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. 8-GEMMASCOPE-RES-16K
    6. 5975
    Prev
    Next
    INDEX
    Explanations

    terms related to broad or generalized concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()?;
    -0.95
    AccessFile
    -0.95
    TemporalType
    -0.92
    ypsies
    -0.90
    évaluateur
    -0.90
    nocache
    -0.89
    ंदीखरीदारी
    -0.88
    uari
    -0.87
     DBNull
    -0.87
    ари
    -0.84
    POSITIVE LOGITS
     Broad
    0.98
    Broad
    0.97
     Brod
    0.94
    broad
    0.93
     BROAD
    0.81
     broad
    0.80
    ([^
    0.79
    bro
    0.70
     Crow
    0.69
     Bro
    0.68
    Activations Density 0.109%

    No Known Activations