© 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. 13676
    Prev
    Next
    INDEX
    Explanations

    instances of the word "release" and its variations

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

    "release"

    np_acts-logits-general · gemini-2.0-flash

    release or released

    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
    RectangleBorder
    -0.92
     femininos
    -0.62
     Савезне
    -0.54
    Personendaten
    -0.54
    ⟬
    -0.54
    Toponymie
    -0.52
    enumi
    -0.52
    CppMethod
    -0.52
     المعيارى
    -0.51
    ViewInit
    -0.51
    POSITIVE LOGITS
     release
    1.41
    release
    1.38
     Release
    1.25
    Release
    1.22
     RELEASE
    1.18
    RELEASE
    1.10
     released
    1.09
     releases
    1.09
    released
    0.99
    releases
    0.99
    Activations Density 0.061%

    No Known Activations