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. 1104
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical representations

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

    Surrounding tokens are "xe2x80x9c" and "xe2x80x9d"

    np_acts-logits-general · gemini-2.0-flash

    quoted text

    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
     않았
    -0.45
    }.
    -0.44
     –
    -0.40
    ترة
    -0.40
    AS
    -0.40
    ca
    -0.40
    sanitize
    -0.39
    5
    -0.39
    ho
    -0.38
    SL
    -0.38
    POSITIVE LOGITS
    tvguidetime
    1.38
     autorytatywna
    1.37
    Hochspringen
    1.19
    Tikang
    1.18
     lenker
    1.07
    enumi
    1.06
     GetEnumerator
    1.05
     EconPapers
    1.04
    expandindo
    1.04
     صوتيه
    1.01
    Activations Density 0.156%

    No Known Activations