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. 70613
    Prev
    Next
    INDEX
    Explanations

    references to sap-related concepts and their effects in biological contexts

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

    sap and related roots

    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
     numerous
    -0.42
     perkara
    -0.37
     resourceCulture
    -0.37
     trzec
    -0.36
     noOf
    -0.36
     various
    -0.36
     nombreuses
    -0.36
    extrême
    -0.36
     Broder
    -0.36
    ria
    -0.35
    POSITIVE LOGITS
     sap
    2.30
     Sap
    2.14
    Sap
    2.13
    sap
    1.93
     SAP
    1.45
    SAP
    1.39
     sapon
    1.22
    sapp
    1.09
     Sapp
    1.09
     Sapi
    1.02
    Activations Density 0.005%

    No Known Activations