© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1301
    Prev
    Next
    INDEX
    Explanations

    instances of procedural language related to legal amendments or court procedures

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

    the presence of certain marker tokens indicating the start of a new sequence or block of text

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

    confirm two people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.55
     zove
    -0.55
    openzeppelin
    -0.52
    ,=
    -0.51
    always
    -0.51
     always
    -0.49
    一颗
    -0.48
     largest
    -0.47
     nyelven
    -0.47
     nunmehr
    -0.47
    POSITIVE LOGITS
    ρέπει
    0.65
    addGap
    0.64
    \{\\
    0.61
     XNUMX
    0.61
    istoitu
    0.60
    onomía
    0.58
    NUMX
    0.58
    rxjs
    0.57
    setAccessible
    0.57
    はじめに
    0.57
    Activations Density 0.001%

    No Known Activations