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. 4505
    Prev
    Next
    INDEX
    Explanations

    references to individuals or personal names associated with various contexts or actions

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

    Capitalized words that start sentences

    np_acts-logits-general · gemini-2.0-flash

    names of people and things

    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
     متعلقه
    -0.99
    ostante
    -0.82
     GoogleFonts
    -0.78
     InputDecoration
    -0.78
    ंदीखरीदारी
    -0.78
     utafitiHapana
    -0.78
     Audiodateien
    -0.76
    DockStyle
    -0.76
    extAlignment
    -0.75
    ContentAsync
    -0.75
    POSITIVE LOGITS
    syl
    0.43
     asciug
    0.43
    hy
    0.43
     Ngh
    0.42
    os
    0.41
     spørs
    0.40
     from
    0.40
    the
    0.40
    uk
    0.40
    ang
    0.40
    Activations Density 0.818%

    No Known Activations