© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15742
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "seem" and its variations indicating perception or subjective observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kaufman
    -0.77
     Ogden
    -0.77
     Bryson
    -0.74
    prefixer
    -0.73
     đức
    -0.73
     législation
    -0.72
     Dane
    -0.71
    yı
    -0.71
    vertx
    -0.71
     Schulz
    -0.68
    POSITIVE LOGITS
     seem
    1.20
     seemed
    1.09
    seem
    1.08
     seems
    1.07
    seems
    1.02
     Seem
    1.02
    seemed
    0.97
    Seems
    0.96
     Seems
    0.89
     sembl
    0.84
    Activations Density 0.021%

    No Known Activations