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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 15119
    Prev
    Next
    INDEX
    Explanations

    question marks and the structure of dialogue, indicating inquiries and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -1.06
    ↵↵↵
    -0.58
    ↵↵↵↵
    -0.58
    !")
    
    -0.52
    </tbody>
    -0.52
    ↵↵↵↵↵
    -0.51
    altra
    -0.48
     bottom
    -0.47
    .*;
    
    -0.47
     whole
    -0.47
    POSITIVE LOGITS
    XmlAccessType
    1.03
     متعلقه
    1.00
    findpost
    0.95
     '\\;'
    0.90
    !*\
    0.90
    ISupport
    0.87
    ագրություններ
    0.86
    ConstraintMaker
    0.85
    tvguidetime
    0.85
    principalColumn
    0.84
    Activations Density 0.167%

    No Known Activations