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. 20-GEMMASCOPE-RES-131K
    6. 120402
    Prev
    Next
    INDEX
    Explanations

    references to various platforms and their functionalities

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

    computing platform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dead
    -0.46
    ||}
    -0.44
    <h4>
    -0.44
    хара
    -0.43
    Dead
    -0.43
     the
    -0.42
    Want
    -0.42
    Demografie
    -0.42
    dead
    -0.40
    قتل
    -0.40
    POSITIVE LOGITS
     PLATFORM
    1.20
     platform
    1.15
    latform
    1.10
     Platform
    1.06
    PLATFORM
    1.05
     Plattform
    1.05
    Platform
    1.04
     plataforma
    1.02
    platform
    1.01
     plateforme
    1.00
    Activations Density 0.006%

    No Known Activations