© 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. 24-GEMMASCOPE-RES-16K
    11. 5270
    Prev
    Next
    INDEX
    Explanations

    references to political parties and their internal dynamics

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

    Comes after "some"

    np_acts-logits-general · gemini-2.0-flash

    some people or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremp
    -0.40
     touch
    -0.35
     만
    -0.35
     pomy
    -0.33
    touch
    -0.33
     plă
    -0.33
     Begegn
    -0.33
    เท
    -0.33
    package
    -0.33
    Poss
    -0.32
    POSITIVE LOGITS
     commentators
    0.68
    səhifə
    0.63
    rungsseite
    0.62
    RectangleBorder
    0.60
     theorists
    0.60
    脚注の使い方
    0.59
    MigrationBuilder
    0.59
    niſſe
    0.58
    ResponseWriter
    0.58
     pund
    0.58
    Activations Density 0.454%

    No Known Activations