© 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. 57672
    Prev
    Next
    INDEX
    Explanations

    conditional phrases related to instructions or guidance

    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
    seamnă
    -0.83
    ir
    -0.68
    ss
    -0.61
    which
    -0.61
    via
    -0.59
    sp
    -0.59
    tritt
    -0.58
    ostante
    -0.58
    re
    -0.58
    ba
    -0.57
    POSITIVE LOGITS
    ]='\
    0.88
     же
    0.85
    ]--;
    0.82
    ']")
    0.81
    "])
    
    0.79
    }')
    0.77
    󠁮
    0.76
    ']]
    0.76
    "]="
    0.76
     procra
    0.75
    Activations Density 0.002%

    No Known Activations