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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15526
    Prev
    Next
    INDEX
    Explanations

    mentions of self-perception and credibility in communication

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

    Preceding words of "seem" or "appear"

    np_acts-logits-general · gemini-2.0-flash

    seems or appears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    deles
    -0.53
     ioutil
    -0.46
    lanco
    -0.43
    ménage
    -0.43
     papillon
    -0.42
    ković
    -0.40
    yethyl
    -0.40
    **********/
    -0.40
    osť
    -0.40
     jegy
    -0.39
    POSITIVE LOGITS
     seeming
    2.25
     seem
    2.11
     seemed
    2.07
    seem
    1.94
     seems
    1.93
     appear
    1.91
     Seem
    1.88
     Seems
    1.88
     appears
    1.85
    seems
    1.85
    Activations Density 0.417%

    No Known Activations