Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 64836
    Prev
    Next
    INDEX
    Explanations

    occurrences of the indefinite article "a" and "an" in various contexts

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

    becoming a new role or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hales
    -0.50
     correlations
    -0.47
     correlation
    -0.47
    예
    -0.46
     Pfund
    -0.46
     disagreements
    -0.46
    المشاركات
    -0.46
     Agree
    -0.46
     Pritchard
    -0.46
    ல்ல
    -0.46
    POSITIVE LOGITS
     become
    1.08
    become
    1.03
     becomes
    0.96
     Become
    0.94
     became
    0.90
    Become
    0.90
    becomes
    0.90
    Becoming
    0.88
     becoming
    0.88
     Became
    0.84
    Activations Density 0.016%

    No Known Activations