© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1286
    Prev
    Next
    INDEX
    Explanations

    language constructs related to method definitions and commands in programming contexts

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

    phrases related to commands involving 'self' and 'with' in a programming context

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

    command groups

    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
     astore
    -0.59
    NewLabel
    -0.57
    argli
    -0.49
     standard
    -0.48
     Mikro
    -0.47
     McAllister
    -0.47
    arino
    -0.46
    Vidite
    -0.46
     secco
    -0.46
    úmenes
    -0.45
    POSITIVE LOGITS
    ynb
    0.58
    Ifc
    0.55
    ImageContext
    0.47
     Reverso
    0.47
    URLException
    0.47
    ToPoint
    0.46
    lotl
    0.46
    Solved
    0.45
    hade
    0.45
     mergeFrom
    0.44
    Activations Density 0.068%

    No Known Activations