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. 18-GEMMASCOPE-RES-16K
    6. 621
    Prev
    Next
    INDEX
    Explanations

    references to data structures and API operations in coding contexts

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

    Code-related keywords and variables

    np_acts-logits-general · gemini-2.0-flash

    code structure keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.55
    </b>
    -0.54
    </u>
    -0.49
    </i>
    -0.48
    </h2>
    -0.47
    ".
    -0.44
    ”.
    -0.42
    ."
    -0.41
    ").
    -0.39
    houette
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    1.14
    SourceChecksum
    1.11
    LookAnd
    0.99
     &___
    0.98
     nahilalakip
    0.94
    ########.
    0.91
    :✨
    0.89
     intptr
    0.87
    WebVitals
    0.86
     Roskov
    0.85
    Activations Density 0.333%

    No Known Activations