© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 4968
    Prev
    Next
    INDEX
    Explanations

    terms related to various forms of input and output in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.92
    SharedCtor
    -0.80
    RTLD
    -0.79
    Parcelize
    -0.78
     métallique
    -0.77
     morire
    -0.77
     antaranya
    -0.76
     jorden
    -0.75
    @[+][
    -0.74
    Smarty
    -0.73
    POSITIVE LOGITS
     INPUT
    1.14
     Input
    1.09
    setInput
    1.07
     input
    1.07
    INPUT
    1.05
     inputs
    1.03
     Inputs
    1.00
    Input
    0.95
     输入
    0.92
    Inputs
    0.85
    Activations Density 0.074%

    No Known Activations