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. 18-GEMMASCOPE-RES-16K
    6. 14368
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evidence and legal discussions

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

    Code snippets or special characters

    np_acts-logits-general · gemini-2.0-flash

    `id:` followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     countless
    -0.64
     innumerable
    -0.53
     hundreds
    -0.48
     many
    -0.47
     thousands
    -0.47
     someone
    -0.46
     every
    -0.46
     strange
    -0.44
     endless
    -0.42
     verur
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.84
     insuffisamment
    0.83
     ExecuteAsync
    0.79
    Commenting
    0.79
     كومونز
    0.78
     referenties
    0.76
     chi̍t
    0.75
    tanleria
    0.75
    findpost
    0.74
    دانشنامهٔ
    0.73
    Activations Density 0.127%

    No Known Activations