© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13684
    Prev
    Next
    INDEX
    Explanations

    the term "raw" and its variations, as well as references to raw materials

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

    "Raw" followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    rawhide, raw materials

    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
     GetEnumerator
    -0.71
     CreateTagHelper
    -0.69
    matchCondition
    -0.64
     plenamente
    -0.60
     rifer
    -0.60
     vícti
    -0.59
    MessageTagHelper
    -0.59
     duquel
    -0.56
    enderror
    -0.56
     nakalista
    -0.56
    POSITIVE LOGITS
     Raw
    1.32
    Raw
    1.20
     raw
    1.19
     RAW
    1.06
    raw
    0.99
    RAW
    0.97
    rawData
    0.75
    hide
    0.73
    getRaw
    0.65
     cruda
    0.63
    Activations Density 0.086%

    No Known Activations