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. 8239
    Prev
    Next
    INDEX
    Explanations

    segments of code or strings related to media organization and statistics

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

    Code, incomplete sentences, or programming terms

    np_acts-logits-general · gemini-2.0-flash

    MRI and court proceedings

    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
     arşivlendi
    -0.58
     arché
    -0.56
    abstractmethod
    -0.56
     stanow
    -0.55
    Tikang
    -0.55
    styleType
    -0.55
    migrationBuilder
    -0.54
    shift
    -0.54
     shifts
    -0.54
    sizeCache
    -0.53
    POSITIVE LOGITS
    </
    0.49
     >=",
    0.47
     getItemCount
    0.47
    )))),
    0.47
    usermodel
    0.46
    protected
    0.45
    ']
    
    0.45
     afer
    0.44
    adpleegd
    0.43
    AutoScale
    0.43
    Activations Density 0.094%

    No Known Activations