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. 7-GEMMASCOPE-RES-16K
    6. 14930
    Prev
    Next
    INDEX
    Explanations

    code structure and import statements in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.64
     localVar
    -0.63
     '\\;'
    -0.51
    Kontrola
    -0.51
    BitmapFactory
    -0.49
     TextInputType
    -0.48
    NOPQRST
    -0.48
    EndContext
    -0.47
     autorytatywna
    -0.46
    Storyboard
    -0.46
    POSITIVE LOGITS
    iconque
    0.67
    ībā
    0.56
    tily
    0.53
    ించ
    0.51
    脚注の使い方
    0.50
    HandleFunc
    0.50
    Personensuche
    0.50
    日閲覧
    0.49
    requireNonNull
    0.49
    istoitu
    0.49
    Activations Density 0.154%

    No Known Activations