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. 23-GEMMASCOPE-RES-16K
    6. 11147
    Prev
    Next
    INDEX
    Explanations

    references to time and events related to player transfers and team lineups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedName
    -0.59
    HasMaxLength
    -0.51
    UrlResolution
    -0.51
     ước
    -0.48
    jspb
    -0.47
    ядок
    -0.47
     numerus
    -0.44
    ristan
    -0.43
    feito
    -0.43
     conjugate
    -0.42
    POSITIVE LOGITS
     side
    0.69
    protoimpl
    0.65
     hosts
    0.63
     بيها
    0.63
     visitors
    0.60
    verwijspagina
    0.58
     club
    0.58
    écnicas
    0.56
    posedge
    0.56
    OGND
    0.55
    Activations Density 0.116%

    No Known Activations