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. 45
    Prev
    Next
    INDEX
    Explanations

    terms associated with technical explanations and specifications

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

    terms related to identity, self-expression, and personal attributes.

    oai_token-act-pair · gpt-4oTriggered 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
    IntoConstraints
    -0.75
    saraba
    -0.74
     Efq
    -0.72
    GOTREF
    -0.71
     itſelf
    -0.71
     pinulongan
    -0.70
    脚注の使い方
    -0.69
     Monfieur
    -0.68
     themſelves
    -0.67
    ſelves
    -0.67
    POSITIVE LOGITS
    ాయి
    0.40
     M
    0.38
     D
    0.36
    Билгалдахарш
    0.35
    ondi
    0.35
     were
    0.35
     Che
    0.34
    ophores
    0.34
     che
    0.34
    abin
    0.34
    Activations Density 0.709%

    No Known Activations