© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 121649
    Prev
    Next
    INDEX
    Explanations

    terms related to legal innocence and evidence of guilt

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

    innocence and exoneration

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     tæ
    -0.36
    weilen
    -0.34
     ocasiones
    -0.33
     uwagę
    -0.29
     aikaa
    -0.28
     práci
    -0.28
     metálica
    -0.26
     endroits
    -0.26
     cuento
    -0.26
     prêts
    -0.25
    POSITIVE LOGITS
     innocence
    0.84
    innocent
    0.81
     exoner
    0.79
    innoc
    0.76
     Guilt
    0.74
     Innocence
    0.74
     guilt
    0.71
     betweenstory
    0.69
    TagMode
    0.69
    Innoc
    0.68
    Activations Density 0.093%

    No Known Activations