© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10562
    Prev
    Next
    INDEX
    Explanations

    expressions of apology or regret

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

    Expressions of apology

    np_acts-logits-general · gemini-2.0-flash

    apologizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraBars
    -0.43
    屓
    -0.42
     prefeitura
    -0.42
    Ведь
    -0.36
     villaggio
    -0.36
     Initiatives
    -0.35
    ToRefresh
    -0.35
    sweise
    -0.35
     enriquec
    -0.34
    FieldBuilder
    -0.34
    POSITIVE LOGITS
     sorry
    1.52
    sorry
    1.44
     SORRY
    1.43
    Sorry
    1.41
     Sorry
    1.39
     apologies
    1.30
     apologize
    1.30
     apologise
    1.28
     apology
    1.27
     apologized
    1.19
    Activations Density 0.150%

    No Known Activations