© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    specific letters or codes associated with certain characters or entities

    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
    <bos>
    -0.73
     Савезне
    -0.47
    r
    -0.46
    u
    -0.42
     дописавши
    -0.42
    Ifc
    -0.41
    UnsafeEnabled
    -0.40
    p
    -0.40
    Референце
    -0.39
    at
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.75
    setVerticalGroup
    0.70
    :+:
    0.66
     &___
    0.63
     stället
    0.61
    fjspx
    0.60
    parsedMessage
    0.60
     المعيارى
    0.58
    writeFieldEnd
    0.58
    存于互联网档案馆
    0.58
    Activations Density 0.262%

    No Known Activations