© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 3180
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with specific entities or important terms in a structured context

    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
    AFX
    -0.50
    — 
    -0.46
    FormTagHelper
    -0.46
    servlet
    -0.45
    ViewImports
    -0.45
     AppBundle
    -0.44
    ագրություններ
    -0.44
    えもん
    -0.44
    veu
    -0.42
    CompilerServices
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.90
    aarrggbb
    0.80
    :+:
    0.77
    msgTypes
    0.76
     doInBackground
    0.69
     PeEnEo
    0.66
    HasForeignKey
    0.65
     ProtoMessage
    0.65
    MigrationBuilder
    0.64
     ModelExpression
    0.64
    Activations Density 1.190%

    No Known Activations