© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10565
    Prev
    Next
    INDEX
    Explanations

    evidence and implications surrounding social and legal accountability

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

    followed by past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    states of affairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    外部リンク
    -0.57
    expandindo
    -0.53
    chyma
    -0.53
     ویکی‌پدیای
    -0.52
    }")]
    -0.51
    ;}
    -0.49
    .
    -0.48
     oprot
    -0.48
    >>()
    -0.47
    igerung
    -0.47
    POSITIVE LOGITS
     chosen
    0.88
     was
    0.81
     did
    0.80
     wasn
    0.71
     grew
    0.70
     became
    0.69
     didn
    0.69
     seemed
    0.69
     assigned
    0.67
     appointed
    0.67
    Activations Density 1.066%

    No Known Activations