© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8443
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and logical connectors in scientific text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dir
    -0.63
    .
    -0.63
    ,
    -0.63
     direction
    -0.60
    :
    -0.60
    lichem
    -0.58
     responsibility
    -0.56
     trans
    -0.56
     services
    -0.55
    aldi
    -0.54
    POSITIVE LOGITS
     Theſe
    0.81
     démocr
    0.79
     GenerationType
    0.79
     quelcon
    0.75
     beginnetje
    0.74
     literaria
    0.74
     ſever
    0.74
     Савезне
    0.74
    HomeAsUpEnabled
    0.74
     Monfieur
    0.73
    Activations Density 0.570%

    No Known Activations