© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 9200
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and keywords in programming, particularly focused on class and method definitions

    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
    aarrggbb
    -1.40
    Obrázky
    -1.38
    IntoConstraints
    -1.38
    AccessorTable
    -1.37
     Administrativna
    -1.35
     CreateTagHelper
    -1.34
    ########.
    -1.29
     فريبيس
    -1.29
     AssemblyTitle
    -1.26
     ―――――
    -1.26
    POSITIVE LOGITS
     
    0.59
     in
    0.56
    .
    0.54
     (
    0.52
     for
    0.51
     or
    0.50
     to
    0.49
    ,
    0.48
     el
    0.48
    /
    0.47
    Activations Density 0.791%

    No Known Activations