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. 108182
    Prev
    Next
    INDEX
    Explanations

    references to plural nouns or specific terms that relate to entities or items

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

    words ending in ies

    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
     MonoBehaviour
    -0.52
    ————————————————
    -0.50
     oprot
    -0.48
    SwingConstants
    -0.47
    Bradford
    -0.46
     Christoph
    -0.46
    Christoph
    -0.45
    httpd
    -0.45
    CreatedAt
    -0.44
     graphql
    -0.43
    POSITIVE LOGITS
    ies
    2.25
    IES
    1.75
    ties
    1.24
    lies
    1.23
     ies
    1.16
    mies
    1.16
     IES
    1.14
    nies
    1.13
    kies
    1.13
    gies
    1.10
    Activations Density 0.010%

    No Known Activations