Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10962
    Prev
    Next
    INDEX
    Explanations

    calls for action or improvement in political and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Need to do something

    np_acts-logits-general · gemini-2.0-flash

    recommendations or necessities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.61
    sizeCache
    -0.57
    almost
    -0.55
    posedge
    -0.53
    canakan
    -0.51
    BufferException
    -0.51
    Almost
    -0.51
    detectChanges
    -0.50
    \{\\
    -0.48
     almost
    -0.48
    POSITIVE LOGITS
     endlich
    1.14
     dringend
    1.02
     reconsider
    0.96
     rethink
    0.90
     urgente
    0.86
     urgently
    0.85
     better
    0.79
     наконец
    0.75
     seriously
    0.75
    reszcie
    0.74
    Activations Density 0.433%

    No Known Activations