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. 633
    Prev
    Next
    INDEX
    Explanations

    titles of films and musical works

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

    Occurrences after the word "The"

    np_acts-logits-general · gemini-2.0-flash

    movie titles and media

    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
    MethodManager
    -0.60
    gestone
    -0.50
    anglès
    -0.48
    ntable
    -0.47
    🍍
    -0.47
    fruta
    -0.46
    typeparam
    -0.46
    zeigt
    -0.46
    fohl
    -0.46
     kaynağından
    -0.45
    POSITIVE LOGITS
    Makefile
    0.56
    सन्दर्भ
    0.56
     RIPRODUZIONE
    0.56
    Files
    0.55
     pngtree
    0.55
    windowFixed
    0.54
     Concentration
    0.54
    titleMargin
    0.53
     firmware
    0.53
    Storage
    0.53
    Activations Density 0.194%

    No Known Activations