© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8662
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities

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

    IRC-style speaker tags in chat logs, especially the angle brackets and the nicknames they enclose.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the opening angle bracket of chat usernames or XML-like tags in IRC chat logs and forum discussions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    twimg
    -0.57
    Gön
    -0.50
     lenker
    -0.49
    倘
    -0.45
     свое
    -0.45
     beschik
    -0.45
    pail
    -0.45
     AppBar
    -0.44
     fv
    -0.44
     cięż
    -0.44
    POSITIVE LOGITS
    帖最后由
    0.81
     Mayor
    0.47
    Gemeinden
    0.42
    BeginContext
    0.41
    Mayor
    0.40
     Jornal
    0.38
    adə
    0.38
    localctx
    0.38
    󠁧
    0.37
     Governor
    0.37
    Activations Density 0.092%

    No Known Activations