© 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. 8-GEMMASCOPE-RES-16K
    6. 6980
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assertion or substantiation of claims

    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
     ſtand
    -0.65
     виправивши
    -0.63
     muſt
    -0.60
    μφωνα
    -0.58
    obic
    -0.55
    Smarty
    -0.55
    hmac
    -0.54
     ſet
    -0.54
    anical
    -0.54
    ſelf
    -0.53
    POSITIVE LOGITS
     that
    1.05
     bahwa
    0.93
     bahawa
    0.91
     faptul
    0.82
     they
    0.80
    that
    0.79
     there
    0.77
     بأن
    0.74
     أنه
    0.72
     rằng
    0.72
    Activations Density 0.702%

    No Known Activations