© 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. 24-GEMMASCOPE-RES-16K
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    concepts related to achieving balance or equilibrium in various contexts

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

    "balance" followed by a preposition or article

    np_acts-logits-general · gemini-2.0-flash

    balance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istoitu
    -0.53
    cstdio
    -0.45
    httphttps
    -0.40
     congrès
    -0.37
     Legion
    -0.37
    WillAppear
    -0.36
     Rudi
    -0.36
     endforeach
    -0.36
    argout
    -0.36
    AndroidJUnit
    -0.35
    POSITIVE LOGITS
     balance
    1.40
    balance
    1.33
     Balance
    1.30
     balancing
    1.30
    Balance
    1.27
     BALANCE
    1.25
     balances
    1.23
     balanced
    1.20
    Balancing
    1.18
    balancing
    1.17
    Activations Density 0.372%

    No Known Activations