© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 866
    Prev
    Next
    INDEX
    Explanations

    programming-related function definitions and their components

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

    Code related to public methods or testing

    np_acts-logits-general · gemini-2.0-flash

    public async Task

    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
    JspWriter
    -0.55
     Allociné
    -0.52
    bewerken
    -0.50
    DoubleQuotes
    -0.50
     فريبيس
    -0.45
    doir
    -0.44
    Réponse
    -0.43
     للمعارف
    -0.42
    ритори
    -0.42
     QtCore
    -0.42
    POSITIVE LOGITS
    __":
    0.67
     test
    0.65
    __':
    0.63
    MigrationBuilder
    0.59
     Económica
    0.58
     négatif
    0.58
    openConnection
    0.57
     fragmentation
    0.56
     testé
    0.56
    richTextPanel
    0.56
    Activations Density 0.032%

    No Known Activations