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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 3433
    Prev
    Next
    INDEX
    Explanations

    phrases discussing opposing views or contradictions

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

    The phrase "to the contrary" or a similar phrase indicating opposition or contradiction to a previously stated point, often found in legal or academic texts.

    eleuther_acts_top20 · gemini-1.5-flashTriggered by @johnny

    phrases that include the word "contrary".

    oai_token-act-pair · gemini-2.0-flashTriggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.73
     BorderRadius
    -0.70
    lidene
    -0.69
    rungsseite
    -0.67
    adeloupe
    -0.63
    fortawesome
    -0.61
    UserScript
    -0.61
    UNDEFINED
    -0.60
    bootstrapcdn
    -0.59
    DidLoad
    -0.58
    POSITIVE LOGITS
     contrast
    0.73
     albeit
    0.70
    albeit
    0.69
     contrary
    0.65
    fraction
    0.63
     Contrast
    0.63
     unlike
    0.62
    contrast
    0.62
     surprising
    0.58
    Nix
    0.58
    Activations Density 0.165%

    No Known Activations