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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 39
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to costs or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.36
     rück
    -0.30
     inspirasi
    -0.29
     Palestinian
    -0.29
    yntaxException
    -0.28
     року
    -0.28
     Duits
    -0.28
    粛
    -0.28
     Roman
    -0.28
     Mainz
    -0.28
    POSITIVE LOGITS
    OGND
    0.63
    esModule
    0.57
    RunWith
    0.56
    ็จ
    0.52
    copg
    0.52
    postmedia
    0.50
    ToProps
    0.50
    verwijspagina
    0.49
    ConstraintMaker
    0.48
    DebuggerNonUser
    0.47
    Activations Density 0.029%

    No Known Activations