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. 8557
    Prev
    Next
    INDEX
    Explanations

    block comments in code

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

    Code, comments, and related programming syntax

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code

    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
    -------------</
    -0.59
    PrototypeOf
    -0.56
    ?,?,
    -0.55
     ejus
    -0.54
    ^(@)
    -0.54
     }</
    -0.54
    mergeFrom
    -0.53
    JsonKey
    -0.53
    ()?;
    -0.53
    xaml
    -0.53
    POSITIVE LOGITS
     utafitiHapana
    0.59
    ↵↵
    0.56
    ↵↵↵
    0.56
     defStyle
    0.55
    MemoryWarning
    0.54
    ↵↵↵↵
    0.52
    __':
    0.49
     >=",
    0.48
    COUVER
    0.47
    Espèce
    0.47
    Activations Density 0.032%

    No Known Activations