© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2968
    Prev
    Next
    INDEX
    Explanations

    numerical or coded data patterns

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

    sequences of numbers or 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
    sizeCache
    -0.55
    ednesdays
    -0.50
    versies
    -0.48
     Económica
    -0.48
     Audiodateien
    -0.47
    Tazama
    -0.47
    Izvori
    -0.45
    -------
    -0.45
    ükemmel
    -0.44
    amilya
    -0.44
    POSITIVE LOGITS
    x
    1.29
    xd
    0.97
    xe
    0.95
    xa
    0.93
    xf
    0.93
    xc
    0.91
    xb
    0.90
    xae
    0.83
    xcf
    0.80
    xfb
    0.77
    Activations Density 0.237%

    No Known Activations