© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3993
    Prev
    Next
    INDEX
    Explanations

    concepts and language related to denial and ignoring reality

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

    "Deny," "denial," or related words

    np_acts-logits-general · gemini-2.0-flash

    denial and acknowledgment

    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
     invokingState
    -0.46
    ynchronously
    -0.46
    ContentAsync
    -0.45
    esgue
    -0.44
    MigrationBuilder
    -0.44
    GrantedAuthority
    -0.43
     draw
    -0.43
     Bioaccumulative
    -0.43
    URLException
    -0.43
    QueryBuilder
    -0.42
    POSITIVE LOGITS
     acknowledging
    0.76
     denial
    0.70
     acknowledge
    0.68
     acknowledges
    0.65
     acknowledgment
    0.64
     denying
    0.64
     acknowledgement
    0.63
    denial
    0.63
     deny
    0.61
    acknowledge
    0.61
    Activations Density 0.395%

    No Known Activations