© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 16071
    Prev
    Next
    INDEX
    Explanations

    types of errors and mistakes, particularly typos and oversights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Portail
    -0.58
    Portail
    -0.58
    dymyr
    -0.55
     שוליים
    -0.54
     countenance
    -0.50
     unrestricted
    -0.49
    WithIOException
    -0.49
     Courant
    -0.49
    endsection
    -0.49
    @[+][
    -0.49
    POSITIVE LOGITS
     mistakes
    1.39
     Mistakes
    1.39
     mistake
    1.26
     errors
    1.25
     erreurs
    1.23
     error
    1.21
     Errors
    1.15
     Mistake
    1.10
     errores
    1.08
     kesalahan
    1.08
    Activations Density 0.501%

    No Known Activations