© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 29040
    Prev
    Next
    INDEX
    Explanations

    patterns indicating denial or evasion of accountability

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

    not admitting or answering excuses

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     createSprite
    -0.58
     ujednoznacz
    -0.45
    Extr
    -0.45
    cuál
    -0.44
    interrup
    -0.42
     fritas
    -0.42
     متعلقه
    -0.40
    synchron
    -0.40
    耳边
    -0.39
    oceros
    -0.38
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.52
    Vidite
    0.46
    sizeCache
    0.46
     nakalista
    0.43
    KommentareTeilen
    0.42
    TRAILING
    0.42
     صوتيه
    0.41
     dAtA
    0.40
    Amicalement
    0.40
    labelledby
    0.38
    Activations Density 0.099%

    No Known Activations