Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15751
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their properties.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    key-value pairs in a structured data format.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    JSON-like structured data, particularly nested objects and arrays with high levels of indentation.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Text snippets containing bracketed content

    np_acts-logits-general · gemini-2.0-flash

    JSON structure definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PostMapping
    -0.47
    ::*;
    -0.46
    ja
    -0.46
     esper
    -0.45
    jam
    -0.45
    jno
    -0.42
     Ma
    -0.42
    ohar
    -0.41
     ay
    -0.41
    <table>
    -0.41
    POSITIVE LOGITS
    styleType
    1.02
    GEBURTSDATUM
    0.95
    SequentialGroup
    0.92
     Baillargeon
    0.89
     propOrder
    0.89
     Référence
    0.89
    principalColumn
    0.89
    WriteAttribute
    0.83
    الإنجليزية
    0.81
     Roskov
    0.76
    Activations Density 0.112%

    No Known Activations