© 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
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 691
    Prev
    Next
    INDEX
    Explanations

    themes related to vulnerable or marginalized populations

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

    vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.56
    WireFormatLite
    -0.52
    seteq
    -0.47
    FromArgb
    -0.45
    Personendaten
    -0.44
    SharedCtor
    -0.43
    XCTAssertEqual
    -0.41
    BufferException
    -0.41
     GetEnumerator
    -0.41
    SpringRunner
    -0.41
    POSITIVE LOGITS
     Homeless
    1.20
     homeless
    1.16
     homelessness
    1.09
     enfans
    0.65
     leſs
    0.63
    Shelter
    0.59
     faſt
    0.59
     juſ
    0.57
     unſ
    0.56
     Shelter
    0.54
    Activations Density 0.006%

    No Known Activations