© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13159
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance and impact of various studies and effects in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Had" followed by a word indicating impact or effect

    np_acts-logits-general · gemini-2.0-flash

    describing impact or effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entreten
    -0.31
     Utiliza
    -0.31
     Presidencia
    -0.31
     Rech
    -0.28
    eriksaan
    -0.28
    ]').
    -0.28
    }")]
    -0.27
     arries
    -0.27
     tră
    -0.27
     dimanche
    -0.27
    POSITIVE LOGITS
     impact
    1.88
     influence
    1.61
    impact
    1.56
     impacts
    1.49
    Impact
    1.45
     affect
    1.44
     Impact
    1.44
     impacto
    1.36
    影響
    1.36
     effect
    1.34
    Activations Density 0.537%

    No Known Activations