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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 107826
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions and responsibilities related to legal or official contexts

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

    sentence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    Detecting section headings or title-like phrases (short, capitalized or emphasized section labels).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.97
     témoig
    -0.85
     geſch
    -0.85
    majánló
    -0.84
     ſehr
    -0.83
    ſehen
    -0.82
    iſchen
    -0.82
     ſelbſt
    -0.81
     wiſſen
    -0.81
    ſchaft
    -0.81
    POSITIVE LOGITS
    The
    0.41
    A
    0.38
    If
    0.37
    When
    0.36
    if
    0.36
     if
    0.36
    Although
    0.36
    L
    0.35
     The
    0.34
    M
    0.33
    Activations Density 0.002%

    No Known Activations