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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8272
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the necessity and presence of particular elements or conditions

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

    prepositional noun phrases in formal prose that link nouns to show possession/association or purpose, especially constructions expressing a need for something.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humaines
    -0.70
     européennes
    -0.65
     normaux
    -0.65
     avancée
    -0.63
     contemporaine
    -0.62
     connues
    -0.61
     fédé
    -0.60
     déterminé
    -0.59
     énergé
    -0.59
     malheureusement
    -0.59
    POSITIVE LOGITS
    ".
    
    0.97
    ########.
    0.95
    )";
    
    0.93
    %;
    
    0.90
    "])
    
    0.90
    ':
    
    0.84
    ='';
    
    0.83
    ":
    
    0.82
     ';
    
    0.82
    ThroughAttribute
    0.81
    Activations Density 0.359%

    No Known Activations