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. 2-GEMMASCOPE-RES-16K
    6. 6773
    Prev
    Next
    INDEX
    Explanations

    elements related to quantitative descriptions, measurements, or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mphony
    -0.65
    LookAnd
    -0.55
    penup
    -0.53
    cyklopedia
    -0.52
    InvalidProtocol
    -0.51
    Carriera
    -0.49
     bunda
    -0.48
    下载附件
    -0.48
    newswire
    -0.48
    tiamo
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.67
    ContentAsync
    0.61
    FTFY
    0.58
    }{*}{}
    0.57
    addContainerGap
    0.55
     ElementRef
    0.54
     AspNetCore
    0.54
    potranspiration
    0.52
    évaluateur
    0.51
    WithMany
    0.51
    Activations Density 1.069%

    No Known Activations