© 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. 14182
    Prev
    Next
    INDEX
    Explanations

    relationships between variables and their dependencies

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

    Subject is dependent on something

    np_acts-logits-general · gemini-2.0-flash

    relies on, depends on, explained by

    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
    ⟬
    -0.54
    ագրություններ
    -0.53
    ⓧ
    -0.52
    DoubleQuotes
    -0.52
    tanleria
    -0.52
    حوالہ
    -0.51
     CreateTagHelper
    -0.50
    rophoto
    -0.49
    ᗕ
    -0.47
     pytest
    -0.46
    POSITIVE LOGITS
    RunWith
    0.40
     rely
    0.36
    DIPSETTING
    0.35
     relying
    0.33
     relies
    0.33
    (!__
    0.33
     саме
    0.31
     právě
    0.30
     kapturem
    0.30
     rests
    0.29
    Activations Density 0.945%

    No Known Activations