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. 14-GEMMASCOPE-RES-16K
    6. 12969
    Prev
    Next
    INDEX
    Explanations

    file paths and source code references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PathVariable
    -0.80
    djangoproject
    -0.80
    ה
    -0.76
     Mays
    -0.74
    endphp
    -0.74
    〕
    -0.72
    もら
    -0.71
    ---*/
    -0.71
     MSA
    -0.69
    kaner
    -0.69
    POSITIVE LOGITS
     src
    1.10
    src
    1.07
    Src
    0.85
     Src
    0.79
    CreateMap
    0.71
     olímp
    0.69
     tutt
    0.69
    Shrimp
    0.68
    Siren
    0.68
     jacquard
    0.67
    Activations Density 0.056%

    No Known Activations