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. 743
    Prev
    Next
    INDEX
    Explanations

    numerical data and formatting within scientific or technical contexts

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

    Citations followed by bracketed numbers

    np_acts-logits-general · gemini-2.0-flash

    journal citations and bibliographic references

    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
    ContentAlignment
    -0.75
    Personensuche
    -0.69
    tagHelperRunner
    -0.67
    Autoritní
    -0.67
    GEBURTSDATUM
    -0.63
    shub
    -0.62
     beginnetje
    -0.62
    NewUrlParser
    -0.61
     minor
    -0.61
     "..\..\..\
    -0.61
    POSITIVE LOGITS
    polate
    0.47
     rémun
    0.43
    ṁ
    0.43
     Longman
    0.42
    crire
    0.41
     Tafel
    0.41
    angulaire
    0.41
     AdapterView
    0.41
     }}}{
    0.41
    COUVER
    0.40
    Activations Density 0.174%

    No Known Activations