© 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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4324
    Prev
    Next
    INDEX
    Explanations

    references to errors and mistakes, particularly in an editorial or procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTDA
    -0.45
    Personendaten
    -0.39
    AddTagHelper
    -0.36
    ècie
    -0.36
     Italijani
    -0.36
     الأص
    -0.35
    pira
    -0.35
    +#+
    -0.34
    Diweddarwch
    -0.34
    DebuggerNonUser
    -0.34
    POSITIVE LOGITS
     mistakes
    2.69
     mistake
    2.59
     errors
    2.56
     error
    2.42
     Mistakes
    2.30
     Errors
    2.22
     errores
    2.14
     erreurs
    2.13
     Fehler
    2.11
     erreur
    2.05
    Activations Density 1.364%

    No Known Activations