© 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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12851
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or occurrence of a condition or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.67
    يكب
    -0.54
     nakalista
    -0.53
    uestamente
    -0.52
    Rüyada
    -0.51
    Tembelea
    -0.50
    RenderAtEndOf
    -0.49
     frischen
    -0.49
     Olivenöl
    -0.48
    pecabe
    -0.48
    POSITIVE LOGITS
    enumi
    0.47
    woordig
    0.47
     was
    0.46
    存于互联网档案馆
    0.45
    literals
    0.42
     The
    0.40
     هو
    0.36
     is
    0.36
     стала
    0.35
    jména
    0.35
    Activations Density 0.187%

    No Known Activations