© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    musical references and mentions of band names or song titles

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

    music-related terms and references to artists or bands

    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
     AssemblyCulture
    -0.67
    nissen
    -0.58
     يتيمه
    -0.55
     المعيارى
    -0.53
    aryen
    -0.50
    tagext
    -0.50
    Sauce
    -0.49
    __*/
    -0.49
     lưu
    -0.49
    一看
    -0.49
    POSITIVE LOGITS
     Xiu
    0.64
     noise
    0.63
    Билгалдахарш
    0.63
     drone
    0.61
     twee
    0.59
     tape
    0.58
     kra
    0.57
     DFA
    0.57
    fax
    0.56
     dron
    0.56
    Activations Density 0.170%

    No Known Activations