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-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1072
    Prev
    Next
    INDEX
    Explanations

    structural elements and syntactic components in code and documentation

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

    results and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.63
     bezeichneter
    -0.60
    Hozzáférés
    -0.58
    ="@+
    -0.57
    MLLoader
    -0.56
     uLocal
    -0.56
     tartalomajánló
    -0.56
    󠁮
    -0.56
    出版年
    -0.56
    URLException
    -0.56
    POSITIVE LOGITS
    ↵↵
    0.85
    ↵
    0.65
    ↵↵↵
    0.39
    </h3>
    0.37
    ↵↵↵↵
    0.37
    </em>
    0.34
     Agency
    0.32
     Marti
    0.32
                           
    0.32
                                   
    0.30
    Activations Density 0.443%

    No Known Activations