© 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. 25-GEMMASCOPE-RES-16K
    11. 6788
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to complex data types and operations

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

    keywords and elements related to mathematical distributions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ("
    -0.89
     ["
    -0.85
     ('
    -0.83
     ()
    -0.82
    []{"
    -0.80
     (“
    -0.79
     ['
    -0.79
     [$
    -0.78
     ())
    -0.77
     («
    -0.77
    POSITIVE LOGITS
    (
    2.00
     (
    0.65
    )(
    0.64
    >(
    0.63
    }(
    0.63
    __(
    0.61
     kasarigan
    0.56
    ,(
    0.56
    _(
    0.55
    ?(
    0.54
    Activations Density 0.307%

    No Known Activations