© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 22775
    Prev
    Next
    INDEX
    Explanations

    questions and explanations related to reasoning and understanding motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anything
    -0.59
    anything
    -0.59
    ξεις
    -0.58
    Anything
    -0.56
    antMatchers
    -0.55
     AssemblyTitle
    -0.54
    ginfo
    -0.54
    ?
    -0.53
    <bos>
    -0.52
     Anything
    -0.52
    POSITIVE LOGITS
    ])));
    0.74
    setVerticalGroup
    0.71
    >
    
    
    0.69
    "]);
    
    0.68
     صوتيه
    0.66
    ")));
    
    0.66
    ())));
    0.65
    "):
    
    0.65
    '):
    
    0.63
    []
    
    0.63
    Activations Density 0.104%

    No Known Activations