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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9576
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms related to debt and lawsuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     osób
    -0.48
     yalnızca
    -0.40
     lidí
    -0.37
     ministros
    -0.37
     člověk
    -0.37
     insanlar
    -0.36
    .
    -0.36
     manusia
    -0.36
     berikut
    -0.36
     sehari
    -0.36
    POSITIVE LOGITS
    ########.
    0.65
     queſta
    0.60
    eroon
    0.60
    ChildScrollView
    0.60
    itets
    0.58
    RenderAtEndOf
    0.58
     encyclo
    0.57
    ituary
    0.57
     Roskov
    0.56
     ་་
    0.54
    Activations Density 1.582%

    No Known Activations