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. 15112
    Prev
    Next
    INDEX
    Explanations

    references to various programming frameworks and data processing protocols

    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
    principalTable
    -0.81
     يتيمه
    -0.73
    __':
    
    -0.72
    Билгалдахарш
    -0.69
    []):
    -0.66
     resourceCulture
    -0.66
    ioutil
    -0.64
    '}>
    -0.64
     ModelExpression
    -0.64
    "):
    
    -0.62
    POSITIVE LOGITS
    /,
    1.20
    /.
    1.16
    /)
    1.13
    /
    1.10
    /?
    1.10
    /"
    1.04
    /*
    1.03
    /",
    1.01
    /',
    1.00
    /</
    0.95
    Activations Density 0.238%

    No Known Activations