© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8408
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or identifiers for groups and characters

    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
    Datuak
    -0.69
    期刊论文
    -0.64
    SequentialGroup
    -0.59
     fitting
    -0.56
     transférez
    -0.52
    })`
    -0.52
    ocarp
    -0.52
     screen
    -0.52
    CONTINUED
    -0.52
     Beagle
    -0.51
    POSITIVE LOGITS
    transQ
    0.65
     useStyles
    0.61
     Italij
    0.60
    nowu
    0.57
     useHistory
    0.56
     tramonto
    0.54
     enää
    0.54
    Viungo
    0.54
     HttpHeaders
    0.54
     braccio
    0.53
    Activations Density 0.114%

    No Known Activations