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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58915
    Prev
    Next
    INDEX
    Explanations

    specific terms related to academic institutions and errors in data or processes

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

    can be, possible, Russian "могут быть"

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Bisnis
    -0.45
    事了
    -0.41
    SerializeField
    -0.41
     startX
    -0.41
    Бі
    -0.40
    Portale
    -0.39
    irus
    -0.39
    anthes
    -0.39
    erba
    -0.38
    paravant
    -0.38
    POSITIVE LOGITS
     dapat
    1.79
     Dapat
    1.29
    dapat
    0.96
    สามารถ
    0.72
     ניתן
    0.69
    extAlignment
    0.68
    CanBe
    0.68
     puede
    0.66
    ניתן
    0.65
    ารถ
    0.64
    Activations Density 0.001%

    No Known Activations