© 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. 388
    Prev
    Next
    INDEX
    Explanations

    contexts related to being "behind" something, suggesting a focus on hidden or underlying aspects

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

    "behind"

    np_acts-logits-general · gemini-2.0-flash

    things behind

    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
    JsonFormat
    -0.46
    område
    -0.42
     păr
    -0.41
     rate
    -0.40
    CppMethod
    -0.40
    \}=
    -0.38
    舘
    -0.38
     prière
    -0.38
    strictEqual
    -0.38
     prayer
    -0.38
    POSITIVE LOGITS
     BEHIND
    1.34
     Behind
    1.31
    Behind
    1.28
    behind
    1.27
     behind
    1.24
    Hinter
    0.94
     derrière
    0.90
     bakom
    0.85
     detrás
    0.84
     Hinter
    0.81
    Activations Density 0.050%

    No Known Activations