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. 10348
    Prev
    Next
    INDEX
    Explanations

    instances of success and recognition in various domains

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

    success and fame

    np_acts-logits-general · gemini-2.0-flash

    success and fame

    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
     متعلقه
    -0.54
     Roskov
    -0.53
     CURLOPT
    -0.51
    Intérieur
    -0.51
    עוד
    -0.48
    ScopeManager
    -0.47
    längerung
    -0.47
    anada
    -0.47
     Biôgrafia
    -0.47
    IsMutable
    -0.47
    POSITIVE LOGITS
     success
    2.29
     succès
    1.93
    success
    1.91
     successful
    1.85
     Success
    1.84
     successo
    1.77
    Success
    1.76
     successes
    1.74
     sucesso
    1.74
     éxito
    1.72
    Activations Density 0.282%

    No Known Activations