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. 1-GEMMASCOPE-RES-16K
    6. 6166
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their configurations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.86
     Administrativna
    -0.67
    expandindo
    -0.65
     Efq
    -0.64
    MsgBox
    -0.64
     rempliss
    -0.63
    ListItemIcon
    -0.60
    RTEX
    -0.60
     HasFactory
    -0.59
    щика
    -0.58
    POSITIVE LOGITS
    PerformLayout
    0.68
    libft
    0.59
    findpost
    0.56
    GroupLayout
    0.55
     AsyncTask
    0.54
    MutableLiveData
    0.54
    createStatement
    0.53
     him
    0.49
    CURLOPT
    0.49
    apunov
    0.49
    Activations Density 0.230%

    No Known Activations