© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 72004
    Prev
    Next
    INDEX
    Explanations

    conditional or hypothetical language suggesting potential actions or outcomes

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

    continue or proceed despite obstacles

    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
    wikidata
    -0.42
    ########.
    -0.40
    новништво
    -0.40
    CPtr
    -0.39
    Personendaten
    -0.38
    unhofer
    -0.38
    Tikang
    -0.36
     poveznice
    -0.35
    CodeDom
    -0.34
    AddTagHelper
    -0.34
    POSITIVE LOGITS
     reluctantly
    0.49
    それでも
    0.47
     nevertheless
    0.47
     Progres
    0.44
     nonetheless
    0.44
     reluct
    0.41
     dennoch
    0.41
     trotzdem
    0.41
    "}";
    0.40
    bukkit
    0.40
    Activations Density 0.091%

    No Known Activations