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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7209
    Prev
    Next
    INDEX
    Explanations

    specific numeric patterns or codes and their respective values in a structured format

    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
    HttpDelete
    -0.53
    EnableWeb
    -0.51
     nawr
    -0.49
    DataPropertyName
    -0.48
    chtenstein
    -0.48
    ⇑
    -0.45
     working
    -0.44
     behind
    -0.43
    erialize
    -0.43
     suit
    -0.42
    POSITIVE LOGITS
     snippetHide
    0.63
    Kaynakça
    0.61
    GHIJKLM
    0.61
    />";
    0.58
     Majefty
    0.57
    Demografia
    0.57
     AttributeSet
    0.57
     InputDecoration
    0.56
    igrette
    0.56
    ExecuteReader
    0.56
    Activations Density 1.201%

    No Known Activations