© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3251
    Prev
    Next
    INDEX
    Explanations

    references to damage and reconstruction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riwal
    -0.48
    MigrationBuilder
    -0.42
     EClass
    -0.41
     indisponible
    -0.41
    iastes
    -0.38
    utebol
    -0.38
    seag
    -0.38
    ChildScrollView
    -0.38
    exitRule
    -0.37
    tilhe
    -0.37
    POSITIVE LOGITS
     damaged
    0.77
     Damaged
    0.71
     reconstruction
    0.69
     damaging
    0.68
     Damage
    0.67
     repair
    0.66
     reconstruct
    0.66
     bescha
    0.65
    Damaged
    0.65
    Reconstruction
    0.65
    Activations Density 1.783%

    No Known Activations