© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10903
    Prev
    Next
    INDEX
    Explanations

    phrases related to political manipulation and the role of government

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

    deceptive tactics and deliberate manipulation of information to mislead audiences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tetto
    -0.49
     onlyOwner
    -0.48
     espont
    -0.42
     समीक्षक
    -0.41
     respek
    -0.40
     powin
    -0.40
    PreferredItem
    -0.40
    exitRule
    -0.39
     considerar
    -0.39
    omitempty
    -0.39
    POSITIVE LOGITS
     pretending
    0.85
     distract
    0.85
     pretext
    0.85
     feign
    0.83
     disguise
    0.83
     pretends
    0.82
     pretended
    0.81
     pretence
    0.81
     guise
    0.81
     excuse
    0.80
    Activations Density 0.825%

    No Known Activations