© 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. 37-GEMMASCOPE-RES-16K
    6. 4967
    Prev
    Next
    INDEX
    Explanations

    programming constructs and parameters related to defining dimensions and properties of graphical components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assembly
    -0.71
     Assembly
    -0.60
     ASSEMBLY
    -0.58
     assemb
    -0.56
     assembling
    -0.55
    Assembly
    -0.54
     assemble
    -0.54
    
    -0.54
                                   
    -0.53
     production
    -0.53
    POSITIVE LOGITS
       
    0.40
     
    0.36
    jsii
    0.36
    Datuak
    0.35
    OGND
    0.35
    CloseOperation
    0.34
    новништво
    0.33
    లాలు
    0.32
    GIVEREF
    0.32
     fejles
    0.31
    Activations Density 0.566%

    No Known Activations