© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3074
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or keywords related to accounts and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -1.03
    findpost
    -1.02
     pleaſure
    -0.99
     Monfieur
    -0.98
     purpoſe
    -0.98
     Diſ
    -0.92
     Reſ
    -0.92
    MigrationBuilder
    -0.91
     مشين
    -0.91
     Anſ
    -0.91
    POSITIVE LOGITS
     d
    0.70
     ve
    0.59
     le
    0.57
     na
    0.55
     m
    0.55
    vir
    0.54
     de
    0.54
    numerusform
    0.53
     tra
    0.52
     ti
    0.51
    Activations Density 0.633%

    No Known Activations