© 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. 18-GEMMASCOPE-RES-16K
    11. 3293
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes or entities, particularly in chemistry and biology contexts

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

    preceding "for," "under," or "as."

    np_acts-logits-general · gemini-2.0-flash

    entities and their functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    -1.02
     sebagai
    -0.79
     sebag
    -0.75
    作为
    -0.74
    作为一个
    -0.69
     как
    -0.67
     jako
    -0.65
    作為
    -0.64
     као
    -0.63
     selaku
    -0.63
    POSITIVE LOGITS
    的一部分
    0.66
    RegressionTest
    0.64
    autaire
    0.61
    ersatz
    0.55
    󠁴
    0.54
    曖昧さ回避
    0.52
     متعلقه
    0.52
    rotz
    0.51
    jgl
    0.51
     during
    0.51
    Activations Density 0.395%

    No Known Activations