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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7826
    Prev
    Next
    INDEX
    Explanations

    financial and legal terminology, particularly related to property and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sogget
    -0.44
     preparazione
    -0.43
    gebob
    -0.43
     initComponents
    -0.41
    libft
    -0.40
    Preparation
    -0.40
     preparación
    -0.40
     BorderSide
    -0.40
    sejarah
    -0.40
     StringTokenizer
    -0.39
    POSITIVE LOGITS
     Chwiliwch
    0.46
     orphaned
    0.44
     Missing
    0.43
     identific
    0.43
     abandoned
    0.42
     unidentified
    0.40
    phans
    0.40
     ब्रेकडाउन
    0.39
    land
    0.39
    UserScript
    0.38
    Activations Density 0.415%

    No Known Activations