© 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. 966
    Prev
    Next
    INDEX
    Explanations

    references to memory and recall-related concepts

    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
    KommentareTeilen
    -0.61
    windowFixed
    -0.59
    ldorf
    -0.56
     OFDb
    -0.55
     Knowing
    -0.52
     /\.(
    -0.52
     /\.
    -0.52
    цездатний
    -0.51
    wykle
    -0.51
    quic
    -0.50
    POSITIVE LOGITS
     fondly
    0.70
    ance
    0.58
     vividly
    0.58
     names
    0.57
    GraphicsUnit
    0.57
    ronyms
    0.53
    fulness
    0.52
    tance
    0.52
    adpleegd
    0.51
    cein
    0.51
    Activations Density 0.126%

    No Known Activations