© 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. 6661
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and code structures

    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
    msgTypes
    -0.52
    
    -0.50
     isNameExpr
    -0.47
    WriteTagHelper
    -0.47
    قایناقلار
    -0.46
    FormTagHelper
    -0.44
    ỡng
    -0.44
     hObject
    -0.43
    ensdag
    -0.43
    MessageOf
    -0.42
    POSITIVE LOGITS
     like
    3.98
     Like
    2.81
     LIKE
    2.58
    Like
    2.56
    like
    2.45
     seperti
    2.39
     như
    2.19
     zoals
    2.02
     como
    1.98
    像
    1.95
    Activations Density 2.085%

    No Known Activations