© 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. 6112
    Prev
    Next
    INDEX
    Explanations

    details related to admission processes and academic achievements

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

    numeric data, measurements, and quantities in instructional or technical contexts.

    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
    ReusableCell
    -0.47
    tagHelperRunner
    -0.39
    ]=>
    -0.38
    BeginInit
    -0.35
     ujednoznacz
    -0.35
    हास
    -0.34
    Aiheesta
    -0.32
     مشين
    -0.32
     zare
    -0.31
    XmlEnum
    -0.31
    POSITIVE LOGITS
     batch
    1.84
     Batch
    1.56
    batch
    1.53
     batches
    1.48
     BATCH
    1.45
    Batch
    1.38
     cohort
    1.38
    BATCH
    1.25
     cohorts
    1.20
     Cohort
    1.16
    Activations Density 0.224%

    No Known Activations