© 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. 16-GEMMASCOPE-RES-16K
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    terms related to variability and intervention in variables or systems

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

    Preceding words include "can," "Brief," "frog," or foreign language

    np_acts-logits-general · gemini-2.0-flash

    verbs after nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    솟
    -0.53
    ్రామ
    -0.53
    stdc
    -0.52
    ypep
    -0.47
     ISOL
    -0.46
    NOSTIC
    -0.44
     fron
    -0.44
     isol
    -0.42
    TokenNameRPAREN
    -0.42
    ทธิ
    -0.41
    POSITIVE LOGITS
    出版年
    0.90
    PhysRevD
    0.67
     EconPapers
    0.67
    InputBorder
    0.63
    expandindo
    0.63
     Normdatei
    0.61
     OFDb
    0.61
    orsese
    0.60
     việc
    0.60
    InjectAttribute
    0.60
    Activations Density 0.793%

    No Known Activations