© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11615
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and criminal history

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

    Follows "no", "prior", or "lack"

    np_acts-logits-general · gemini-2.0-flash

    prior criminal convictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     descomp
    -0.38
    ("")]
    -0.36
     virš
    -0.32
    ToMap
    -0.31
    ทำ
    -0.30
    étro
    -0.30
     avan
    -0.29
     formular
    -0.29
    })();
    -0.29
    iecie
    -0.29
    POSITIVE LOGITS
     criminal
    0.85
     convictions
    0.77
    criminal
    0.74
     felony
    0.74
     convicted
    0.73
    Criminal
    0.72
     felon
    0.69
     ujednoznacz
    0.69
     Criminal
    0.66
    曾
    0.64
    Activations Density 0.772%

    No Known Activations