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. 17-GEMMASCOPE-RES-16K
    6. 13278
    Prev
    Next
    INDEX
    Explanations

    hexadecimal values and associated numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.95
    GEBURTSDATUM
    -0.71
    colgroup
    -0.70
     Referential
    -0.70
    SequentialGroup
    -0.70
    ⓧ
    -0.69
    onAttach
    -0.67
    istoitu
    -0.62
    hasMoreElements
    -0.60
    WriteAttribute
    -0.60
    POSITIVE LOGITS
     Diſ
    0.61
     ſta
    0.60
     miſ
    0.57
     efficacité
    0.56
     deſt
    0.55
     dedans
    0.55
     dieß
    0.55
    DotNetBar
    0.55
     uſed
    0.55
     ſur
    0.54
    Activations Density 0.833%

    No Known Activations