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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 3743
    Prev
    Next
    INDEX
    Explanations

    numerical references or citations within the text

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

    Integers

    np_acts-logits-general · gemini-2.0-flash

    line numbers or codes

    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
     szóci
    -0.86
    ☸
    -0.79
    Datuak
    -0.77
     nahilalakip
    -0.72
    StructEnd
    -0.71
    Hauptartikel
    -0.69
    Portale
    -0.66
    GEBURTSDATUM
    -0.66
    下载附件
    -0.64
    posedge
    -0.63
    POSITIVE LOGITS
    4
    1.01
    8
    0.96
    6
    0.96
    5
    0.96
    9
    0.96
    2
    0.92
    3
    0.91
    7
    0.90
    0
    0.87
    1
    0.82
    Activations Density 1.000%

    No Known Activations