© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 164
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring or assessment systems

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

    "score" or "scores"

    np_acts-logits-general · gemini-2.0-flash

    score of or on

    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
    expandindo
    -0.82
     ostavi
    -0.72
     resourceCulture
    -0.70
     متعلقه
    -0.62
     ""))
    -0.60
    isations
    -0.59
    Kaynakça
    -0.59
     تضيفلها
    -0.58
     مشين
    -0.58
    Hyde
    -0.57
    POSITIVE LOGITS
     Scores
    0.98
     scores
    0.98
    scores
    0.92
    Scores
    0.87
    card
    0.84
     Scor
    0.83
     scored
    0.83
    Scor
    0.80
     scor
    0.76
     Score
    0.76
    Activations Density 0.118%

    No Known Activations