© 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. 24-GEMMASCOPE-RES-16K
    11. 4661
    Prev
    Next
    INDEX
    Explanations

    phrases related to ratings and evaluations of value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Chinese language related words

    np_acts-logits-general · gemini-2.0-flash

    sorting by most recent, oldest, or favorite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.79
    RenderAtEndOf
    -0.73
    MemoryWarning
    -0.58
    SourceChecksum
    -0.56
    AsUp
    -0.56
    SPATH
    -0.56
    Clik
    -0.55
    StoryboardSegue
    -0.54
     initComponents
    -0.51
     Reverso
    -0.51
    POSITIVE LOGITS
     abgerufen
    0.60
     irres
    0.52
     विश्वसनीयता
    0.51
    不容
    0.51
     intptr
    0.50
    消
    0.49
    inoma
    0.49
     Saltar
    0.49
    }")
    0.48
    }")
    0.48
    Activations Density 0.011%

    No Known Activations