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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4577
    Prev
    Next
    INDEX
    Explanations

    words related to pending actions or incomplete processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.74
    ündig
    -0.63
    moveToFirst
    -0.58
    fastjson
    -0.54
    tometer
    -0.54
    ništvo
    -0.54
     thiệu
    -0.54
     саны
    -0.54
    RTHOOK
    -0.53
     pageContext
    -0.53
    POSITIVE LOGITS
     yet
    0.76
     belum
    0.74
     undecided
    0.70
     undetermined
    0.69
     Aún
    0.67
     هنوز
    0.67
     todavía
    0.66
    GEBURTSDATUM
    0.65
     chưa
    0.65
    queryInterface
    0.64
    Activations Density 0.361%

    No Known Activations