© 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. 15972
    Prev
    Next
    INDEX
    Explanations

    terms related to expansion and growth

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

    the word "expansion" or its variants in context.

    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
    LookAnd
    -0.63
    KommentareTeilen
    -0.59
     autorytatywna
    -0.49
     الوطنيه
    -0.48
     surla
    -0.48
    pushFollow
    -0.47
    حياته
    -0.45
    ագրություններ
    -0.43
    __':
    -0.41
    èdia
    -0.41
    POSITIVE LOGITS
     expansion
    1.34
     Expansion
    1.31
     expansions
    1.23
    Expansion
    1.23
    expansion
    1.22
     expand
    1.21
     Expanding
    1.21
    Expanding
    1.18
     Expand
    1.18
     expanding
    1.18
    Activations Density 0.124%

    No Known Activations