© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16101
    Prev
    Next
    INDEX
    Explanations

    numerical values related to legal or statistical contexts

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

    legal citations in court documents (case names, statute references, and page numbers).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.40
     MaterialApp
    -0.39
    iastes
    -0.39
    adaptiveStyles
    -0.38
    seamnă
    -0.36
    WriteTagHelper
    -0.35
    Personendaten
    -0.35
    dps
    -0.34
     CanadaChoose
    -0.33
     catho
    -0.32
    POSITIVE LOGITS
    ніципалі
    0.63
    ########.
    0.44
    Segoe
    0.42
    ɵɵ
    0.41
    __.__
    0.40
    yfikacja
    0.40
     Hald
    0.40
    Topping
    0.39
    Tpl
    0.39
     unsus
    0.39
    Activations Density 0.597%

    No Known Activations