© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5143
    Prev
    Next
    INDEX
    Explanations

    expressions of self-awareness and personal reflection

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

    Preceding words of attributes or qualities

    np_acts-logits-general · gemini-2.0-flash

    various contexts followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
     miniaturka
    -0.56
     enfans
    -0.54
     hierzu
    -0.54
     hidráulica
    -0.52
     čierna
    -0.51
     Administração
    -0.50
     übrigen
    -0.50
     griechischen
    -0.50
     geholfen
    -0.50
     bowiem
    -0.50
    POSITIVE LOGITS
     fuckin
    0.62
     fucking
    0.56
     weirdly
    0.49
     fucked
    0.48
     really
    0.45
     kinda
    0.43
     pretty
    0.43
     weird
    0.43
     psychologically
    0.43
     shitty
    0.42
    Activations Density 0.268%

    No Known Activations