Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8042
    Prev
    Next
    INDEX
    Explanations

    verbs indicating influence, inspiration, and significant actions related to change or events

    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
    BY
    -1.95
    By
    -1.63
     By
    -1.47
    by
    -1.41
     BY
    -1.30
    bys
    -1.05
    getBy
    -0.89
    FROM
    -0.89
    ListBy
    -0.84
    ByKey
    -0.83
    POSITIVE LOGITS
     my
    0.74
     bu
    0.55
    }');
    0.54
     buy
    0.53
     <<<<<<<<<<<<<<
    0.53
     be
    0.52
    PRNewswire
    0.48
    wikidata
    0.47
    ))->
    0.47
    _))
    0.47
    Activations Density 0.425%

    No Known Activations