© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6754
    Prev
    Next
    INDEX
    Explanations

    references to time and temporal phrases

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

    punctuation marks, particularly commas.

    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
    ​,
    -0.35
    );
    
    
    -0.33
    ,​
    -0.33
     OnInit
    -0.33
    ,&
    -0.32
    座
    -0.31
    <caption>
    -0.31
     ​
    -0.30
    (&$
    -0.30
     ―
    -0.30
    POSITIVE LOGITS
    SBATCH
    0.69
    Geplaatst
    0.59
    LookAnd
    0.59
    #+#
    0.57
    ScopeManager
    0.56
    writeField
    0.55
    ########.
    0.55
    AccessorTable
    0.54
    Šaltiniai
    0.54
    principalColumn
    0.54
    Activations Density 0.048%

    No Known Activations