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. 15-GEMMASCOPE-RES-16K
    6. 2756
    Prev
    Next
    INDEX
    Explanations

    structures that indicate changes in narrative or argumentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -1.06
     المعيارى
    -1.03
    mybatisplus
    -0.99
     JpaRepository
    -0.94
    DOCTYPE
    -0.94
    ----</
    -0.93
    featureID
    -0.91
    -------------</
    -0.88
     GenerationType
    -0.88
     تضيفلها
    -0.86
    POSITIVE LOGITS
     The
    1.12
    The
    1.07
    There
    0.93
     There
    0.92
    When
    0.87
     When
    0.87
     If
    0.85
    If
    0.84
    To
    0.75
    While
    0.75
    Activations Density 0.178%

    No Known Activations