Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35540
    Prev
    Next
    INDEX
    Explanations

    instances of the word "was," indicating a focus on past-tense descriptions or states

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

    expressing a past thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.55
    RenderAtEndOf
    -0.54
    ModelAdmin
    -0.52
     CURIAM
    -0.50
     EClass
    -0.50
     BoxFit
    -0.50
    bewerken
    -0.49
    PMailer
    -0.48
     fraî
    -0.48
    principalColumn
    -0.48
    POSITIVE LOGITS
    possibly
    0.47
     maybe
    0.46
     possibly
    0.43
    maybe
    0.43
    Possibly
    0.42
    																															
    0.40
    是不是
    0.40
    Maybe
    0.40
    really
    0.40
     probably
    0.39
    Activations Density 0.068%

    No Known Activations