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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7611
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and statistics related to measurements and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.59
    =$?
    -0.58
    ftagPool
    -0.56
    expandindo
    -0.54
     TestBed
    -0.53
     BorderSide
    -0.53
     '\\;'
    -0.51
    stateMutability
    -0.51
    SaveChangesAsync
    -0.49
     Different
    -0.48
    POSITIVE LOGITS
     counterparts
    0.99
     counterpart
    0.88
     comparable
    0.83
     previous
    0.75
     milik
    0.75
     corresponding
    0.71
     ones
    0.71
     similar
    0.69
     celui
    0.69
     sebelumnya
    0.68
    Activations Density 1.191%

    No Known Activations