© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 523
    Prev
    Next
    INDEX
    Explanations

    expressions related to small, significant details and accomplishments

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

    phrases emphasizing small or minor details, actions, or incremental changes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    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
    -0.54
    transQ
    -0.48
    enterOuterAlt
    -0.45
    IndentedString
    -0.44
    amoan
    -0.42
    Personendaten
    -0.42
    msgTypes
    -0.42
     apellidos
    -0.41
     насељу
    -0.41
     يتيمه
    -0.40
    POSITIVE LOGITS
     small
    1.56
     minor
    1.49
     tiny
    1.41
    small
    1.41
     pequeños
    1.32
     pequenas
    1.30
     piccoli
    1.30
     piccole
    1.28
     little
    1.28
     kleine
    1.27
    Activations Density 0.579%

    No Known Activations