Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8078
    Prev
    Next
    INDEX
    Explanations

    specific legal citations and references within legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -0.37
    varargin
    -0.34
     soeur
    -0.33
     הנו
    -0.33
    HOT
    -0.33
    ⓧ
    -0.33
    jScrollPane
    -0.32
     Comprometido
    -0.32
    Архівовано
    -0.30
    Alguien
    -0.30
    POSITIVE LOGITS
    IntoConstraints
    0.62
     supra
    0.55
    slip
    0.52
     Slip
    0.52
    Slip
    0.51
    supra
    0.51
    -------
    0.50
    infra
    0.50
    +#+#
    0.48
     slip
    0.48
    Activations Density 1.552%

    No Known Activations