Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2388
    Prev
    Next
    INDEX
    Explanations

    elements related to legal discussions and judgments

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

    Attribution, quotation, or speech

    np_acts-logits-general · gemini-2.0-flash

    reporting speech or statements

    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
    setTypeface
    -0.65
    OrNil
    -0.50
     XCTest
    -0.49
     {};
    
    -0.47
    ForType
    -0.46
     برانيه
    -0.46
    bootstrapcdn
    -0.45
    endforeach
    -0.45
    μαι
    -0.44
    "];
    
    -0.44
    POSITIVE LOGITS
     saying
    2.79
    saying
    2.30
     stating
    2.23
    Saying
    2.05
     noting
    2.05
     Saying
    1.99
     citing
    1.88
     diciendo
    1.82
     sayin
    1.75
     dizendo
    1.70
    Activations Density 0.426%

    No Known Activations