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. 24-GEMMASCOPE-RES-16K
    6. 8051
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or questions about communication and their dynamics

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

    Negative responses followed by a resolution

    np_acts-logits-general · gemini-2.0-flash

    affirmative or negative responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '])->
    -0.74
    //{
    
    -0.63
    |}{$
    -0.63
     \
    
    -0.60
     صوتيه
    -0.59
     [{
    
    -0.58
    \
    
    -0.57
    ciless
    -0.57
    "+
    
    -0.57
     thereby
    -0.57
    POSITIVE LOGITS
     inderdaad
    0.99
    ...@
    0.90
     AssemblyCulture
    0.77
    ....
    0.72
    .....
    0.69
    FTFY
    0.68
     downvoted
    0.68
    ......
    0.66
    ........
    0.66
    .......
    0.65
    Activations Density 0.547%

    No Known Activations