© 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. 3-GEMMASCOPE-RES-16K
    11. 8111
    Prev
    Next
    INDEX
    Explanations

    statements related to significance and interest in research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteMapping
    -0.60
     vPvB
    -0.54
    ClientSize
    -0.50
    ModelAdmin
    -0.45
    WaitGroup
    -0.43
    ின்ற
    -0.43
    OPTS
    -0.42
    h
    -0.41
    E
    -0.41
    ContextHolder
    -0.40
    POSITIVE LOGITS
    tably
    0.76
    Hochspringen
    0.75
     "..\..\
    0.68
    =$?
    0.66
    etheless
    0.65
     TextAppearance
    0.64
    igshid
    0.62
    GeneratedCode
    0.62
    Geplaatst
    0.62
     Hein
    0.62
    Activations Density 0.385%

    No Known Activations