© 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. 5084
    Prev
    Next
    INDEX
    Explanations

    references to societal norms and issues surrounding racial dynamics

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

    Sentences expressing disagreement or contradiction

    np_acts-logits-general · gemini-2.0-flash

    but that's wrong

    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
     setEmail
    -0.44
    \{\\
    -0.42
     MonoBehaviour
    -0.42
    spesies
    -0.42
    omethyl
    -0.40
    PreInfinity
    -0.40
    Sklici
    -0.39
    toplankton
    -0.39
    kháu
    -0.39
    testid
    -0.39
    POSITIVE LOGITS
     Wrong
    0.52
    錯
    0.49
     incorrect
    0.48
     saites
    0.48
    Wrong
    0.47
     erroneous
    0.46
     WRONG
    0.45
    WRONG
    0.45
     Incorrect
    0.44
     untrue
    0.42
    Activations Density 0.421%

    No Known Activations