© 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. 15-GEMMASCOPE-RES-16K
    6. 8509
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.89
     myſelf
    -0.88
     auffi
    -0.87
     pleaſure
    -0.86
     poffible
    -0.85
     houſe
    -0.82
     ſtate
    -0.80
    ſelves
    -0.77
     cauſe
    -0.77
     purpoſe
    -0.77
    POSITIVE LOGITS
     apparently
    0.93
     IIRC
    0.89
    (?)
    0.88
     (?)
    0.85
     actually
    0.82
     iirc
    0.82
     pretty
    0.81
    apparently
    0.81
     basically
    0.81
     guy
    0.78
    Activations Density 0.463%

    No Known Activations