© 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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7278
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web routing and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.44
     Convert
    -0.44
    AnimationsModule
    -0.43
    getitem
    -0.42
     onBind
    -0.42
    bootstrapcdn
    -0.42
    UnusedPrivate
    -0.42
     Mitar
    -0.42
     LB
    -0.41
    sendRedirect
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.42
    帖最后由
    0.42
     Administrativna
    0.38
    
    0.35
     démission
    0.35
     palsu
    0.35
     erity
    0.34
     Städ
    0.34
     Wiktionnaire
    0.34
     szár
    0.33
    Activations Density 0.310%

    No Known Activations