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. 16-GEMMASCOPE-RES-16K
    6. 12902
    Prev
    Next
    INDEX
    Explanations

    non-activated content or sections without relevant information

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

    Code, interfaces, and technical documentation

    np_acts-logits-general · gemini-2.0-flash

    code following special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WaitGroup
    -0.70
     étoit
    -0.67
    .~(\
    -0.61
     auffi
    -0.61
    arraycopy
    -0.61
    tablename
    -0.60
     sánchez
    -0.60
     étoient
    -0.59
    principalColumn
    -0.59
     amitié
    -0.58
    POSITIVE LOGITS
     Taktlose
    0.57
    ')):
    0.56
    ьаж
    0.53
    SourceChecksum
    0.51
    piram
    0.51
    </h2>
    0.49
     naviguant
    0.48
    __':
    
    0.48
    </h4>
    0.47
    ρίες
    0.47
    Activations Density 0.032%

    No Known Activations