© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1340
    Prev
    Next
    INDEX
    Explanations

    programming-related terms that denote data types or structures

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

    Protocol buffer data structures

    np_acts-logits-general · gemini-2.0-flash

    debug logs with colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    AddTagHelper
    -0.63
     Muta
    -0.57
     enfans
    -0.56
    isContained
    -0.53
    IUrlHelper
    -0.50
     invokingState
    -0.50
    #+#
    -0.49
    mybatisplus
    -0.49
    writeFieldEnd
    -0.48
    JspWriter
    -0.47
    POSITIVE LOGITS
     ErrIntOverflow
    0.44
     pungkasnya
    0.42
     pungkas
    0.41
    niosek
    0.35
     mergeFrom
    0.34
    bangan
    0.33
     protocol
    0.33
     informations
    0.32
    ACKS
    0.32
     inter
    0.32
    Activations Density 1.129%

    No Known Activations