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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8766
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and action-taking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Verb "go" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    going with or choosing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []
    -1.30
     []
    -1.10
    [][]
    -1.07
    [][
    -0.97
    []{
    -0.96
    []"
    -0.81
    [,]
    -0.79
    [],
    -0.79
    [];
    -0.78
    [
    -0.77
    POSITIVE LOGITS
    )");
    
    0.65
    '>
    
    0.61
    RenderAtEndOf
    0.60
    "):
    
    0.59
    '}>
    0.58
    '>{
    0.58
    '>"
    0.56
    ">'
    0.55
    )_/¯
    0.55
    ])),
    0.55
    Activations Density 0.098%

    No Known Activations