© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80845
    Prev
    Next
    INDEX
    Explanations

    terms related to critical assessment or qualitative evaluation

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

    maliciously, indistinguishable, mitigates, solidifying, collaborates, criticizes, reaffirms

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    _
    -0.77
    -
    -0.66
    <td>
    -0.52
    displaystyle
    -0.51
    ,
    -0.50
    的
    -0.49
    ↵
    -0.48
    <eos>
    -0.47
    \_
    -0.45
     &
    -0.44
    POSITIVE LOGITS
     فريبيس
    0.89
    BibitemShut
    0.81
    AddTagHelper
    0.79
    iſen
    0.76
    ientras
    0.76
     belangrij
    0.75
    iffance
    0.75
    XmlAccessType
    0.75
     iſt
    0.74
     snippetHide
    0.74
    Activations Density 0.077%

    No Known Activations