© 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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104625
    Prev
    Next
    INDEX
    Explanations

    colons and their frequency in the context of timestamps or time-related data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kohdetta
    -0.42
    providedIn
    -0.38
    Traducción
    -0.36
     Италијани
    -0.34
    Capítulo
    -0.34
    رشف
    -0.33
    STRICT
    -0.32
    ⓧ
    -0.31
    зулта
    -0.31
    誠
    -0.31
    POSITIVE LOGITS
    KommentareTeilen
    0.58
    entibus
    0.56
    subsubsection
    0.55
     WaitForSeconds
    0.48
    aarrggbb
    0.47
     يتيمه
    0.47
     avoient
    0.47
     CreateTagHelper
    0.46
     Timeout
    0.46
    entant
    0.46
    Activations Density 0.001%

    No Known Activations