© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12563
    Prev
    Next
    INDEX
    Explanations

    key syntactic structures and important components in code syntax

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

    Objective-C keywords

    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
     يتيمه
    -0.49
     estekak
    -0.47
    ViewFeatures
    -0.47
    テンツ
    -0.47
    舺
    -0.46
     незавершена
    -0.46
    internalType
    -0.44
     numerus
    -0.44
     avulla
    -0.44
    eseorang
    -0.44
    POSITIVE LOGITS
     survived
    0.44
    rative
    0.41
     geodes
    0.41
    stateProvider
    0.40
    nonatomic
    0.40
    instancetype
    0.40
     صالح
    0.40
    ence
    0.39
     super
    0.38
     MAE
    0.38
    Activations Density 0.019%

    No Known Activations