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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9789
    Prev
    Next
    INDEX
    Explanations

    expressions or phrases related to speaking and communication.

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

    numerical values and coding-related terms.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    verbs related to communication or speech, particularly in the present tense.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
    DoubleQuotes
    -0.97
     للاسماء
    -0.96
    tagHelperRunner
    -0.84
     تضيفلها
    -0.81
    Попис
    -0.80
    دانشنامهٔ
    -0.76
    ⓧ
    -0.71
    actionMode
    -0.70
    rungsseite
    -0.70
     clearColor
    -0.70
    POSITIVE LOGITS
     speaking
    0.98
     speak
    0.97
     speaks
    0.93
     spoke
    0.93
     Speak
    0.87
     Speaking
    0.86
    Speaking
    0.84
     spoken
    0.82
    SPE
    0.82
    Speak
    0.80
    Activations Density 0.055%

    No Known Activations