© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13669
    Prev
    Next
    INDEX
    Explanations

    various metrics and characteristics associated with user preferences and contexts

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

    preceding negative affixes or qualities

    np_acts-logits-general · gemini-2.0-flash

    word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    “
    -0.36
    .
    -0.30
    ósitos
    -0.28
    My
    -0.28
    :
    -0.27
    La
    -0.27
    sekret
    -0.27
    1
    -0.26
     “
    -0.26
    El
    -0.26
    POSITIVE LOGITS
    MigrationBuilder
    0.74
     שוליים
    0.72
     препратки
    0.71
    يميديا
    0.69
    səhifə
    0.68
    ########.
    0.67
     nakalista
    0.66
     MainAxisSize
    0.65
    AddHtmlAttribute
    0.64
     Roskov
    0.64
    Activations Density 0.718%

    No Known Activations