© 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. 7-GEMMASCOPE-RES-16K
    6. 8630
    Prev
    Next
    INDEX
    Explanations

    references to paths or routes in textual descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtate
    -0.88
     purpoſe
    -0.83
     noft
    -0.78
     Majefty
    -0.77
    gants
    -0.77
     ſmall
    -0.77
     ſta
    -0.75
     Efq
    -0.74
     Conſ
    -0.74
     perſon
    -0.73
    POSITIVE LOGITS
     camino
    0.88
     journey
    0.76
    journey
    0.67
    way
    0.65
     drodze
    0.65
     along
    0.64
    דרך
    0.64
     cesty
    0.64
     caminho
    0.63
     menuju
    0.62
    Activations Density 0.111%

    No Known Activations