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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 80269
    Prev
    Next
    INDEX
    Explanations

    function calls and error handling in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    OGND
    -0.66
     FetchType
    -0.56
    ModelSerializer
    -0.49
    EndGlobalSection
    -0.47
    nezeu
    -0.47
    Diweddarwch
    -0.47
    pulumi
    -0.45
    ModelForm
    -0.44
     useAppContext
    -0.44
     kaarangay
    -0.44
    POSITIVE LOGITS
     perdiendo
    0.38
    lably
    0.37
    QtWidgets
    0.36
     banderas
    0.36
     nervioso
    0.35
    DIPSETTING
    0.35
    Distribuzione
    0.35
     another
    0.35
    warnai
    0.35
    Errorf
    0.35
    Activations Density 0.012%

    No Known Activations