© 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. 4-GEMMASCOPE-RES-16K
    6. 345
    Prev
    Next
    INDEX
    Explanations

    phrases questioning existence, meaning, and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ांकि
    -0.54
    ori
    -0.48
    пле
    -0.47
     lat
    -0.46
    jas
    -0.45
     opgenomen
    -0.44
    era
    -0.44
     Ple
    -0.43
    siez
    -0.43
    és
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
     propOrder
    0.79
     Roskov
    0.77
    انيف
    0.65
     what
    0.65
     zirc
    0.65
     hva
    0.64
     يتيمه
    0.63
    archiviato
    0.63
    cplusplus
    0.63
    Activations Density 0.296%

    No Known Activations