© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 90269
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to timing and assessment in various contexts, particularly focusing on timing in processes and evaluations

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

    early stages or not yet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.56
    /**
    -0.53
    Бахар
    -0.51
    ">//
    -0.50
    ]")]
    -0.49
    /*
    -0.49
     protoimpl
    -0.48
    GEBURTSDATUM
    -0.48
    AddTagHelper
    -0.48
    ViewFeatures
    -0.47
    POSITIVE LOGITS
    まだ
    0.46
     belum
    0.45
     immature
    0.43
     chưa
    0.42
     todavía
    0.41
    まだまだ
    0.39
    はまだ
    0.39
    未
    0.39
     temprana
    0.38
     masih
    0.38
    Activations Density 0.193%

    No Known Activations