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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 12843
    Prev
    Next
    INDEX
    Explanations

    key processes and conditions important for scientific experimentation and research methodologies

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

    the preposition "to" used in infinitive constructions and purpose clauses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.60
    ThroughAttribute
    -0.57
    XmlAccessType
    -0.56
    SequentialGroup
    -0.56
     propOrder
    -0.54
    URLException
    -0.52
    queryInterface
    -0.52
    ftagPool
    -0.50
    IUrlHelper
    -0.49
     насељу
    -0.49
    POSITIVE LOGITS
     avoid
    2.16
     avoiding
    2.02
     avoids
    1.94
    avoid
    1.88
     Avoid
    1.84
     avoided
    1.78
    Avoid
    1.77
     prevent
    1.76
    避免
    1.71
    Avoiding
    1.70
    Activations Density 0.920%

    No Known Activations