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. 7-GEMMASCOPE-RES-16K
    6. 9450
    Prev
    Next
    INDEX
    Explanations

    references to publication details, particularly volume and page numbers in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()}>
    -0.58
    }>
    -0.57
    <eos>
    -0.56
    ...
    -0.55
    })-
    -0.55
    外部連結
    -0.53
    "}>
    -0.53
    ↵
    -0.52
    ())){
    -0.52
     Schles
    -0.51
    POSITIVE LOGITS
     pp
    1.80
    pp
    1.25
     Pp
    1.14
     PP
    1.05
    PP
    1.03
    Pp
    1.01
    msgSender
    0.96
    ppc
    0.93
     Sepp
    0.92
    躇
    0.85
    Activations Density 0.081%

    No Known Activations