© 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. 2-GEMMASCOPE-RES-16K
    6. 1278
    Prev
    Next
    INDEX
    Explanations

    references to hooks in various contexts, particularly in relation to devices or mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.73
     Stedman
    -0.59
     spad
    -0.55
     Sorge
    -0.52
     Weid
    -0.52
     Legacy
    -0.52
     artery
    -0.51
    orphism
    -0.51
     ſche
    -0.51
     Vance
    -0.51
    POSITIVE LOGITS
     lat
    0.90
     hook
    0.86
     scratch
    0.86
     HOOK
    0.86
     hooking
    0.84
     Lat
    0.83
     hooked
    0.82
    Lat
    0.81
     LAT
    0.81
    lat
    0.79
    Activations Density 0.106%

    No Known Activations