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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 74320
    Prev
    Next
    INDEX
    Explanations

    indicative state verbs in the present and past tense

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

    is phrases

    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
    >\<^
    -0.60
    groupName
    -0.54
     Knud
    -0.54
    Guer
    -0.54
    ulemon
    -0.52
    createNew
    -0.52
     Nunn
    -0.52
     idéia
    -0.52
    Lau
    -0.52
     Vau
    -0.52
    POSITIVE LOGITS
     ist
    1.32
     Ist
    0.91
     sind
    0.90
    Ist
    0.83
     nakalista
    0.81
     είναι
    0.75
     is
    0.73
     är
    0.70
     è
    0.68
     está
    0.67
    Activations Density 0.001%

    No Known Activations