© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 426
    Prev
    Next
    INDEX
    Explanations

    comments and documentation within code or technical text

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

    Code comments or non-English text

    np_acts-logits-general · gemini-2.0-flash

    Source In

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     المعيارى
    -0.45
    jsoup
    -0.44
    pausal
    -0.43
    ────
    -0.41
    herself
    -0.41
     tagging
    -0.41
    gud
    -0.40
     bronze
    -0.39
     hornear
    -0.39
    bronze
    -0.38
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.59
     beginnetje
    0.49
    styleable
    0.48
    Билгалдахарш
    0.48
     utafitiHapana
    0.46
    InlineData
    0.45
     onPostExecute
    0.45
     CreateTagHelper
    0.45
     invokingState
    0.44
     nonUne
    0.43
    Activations Density 0.398%

    No Known Activations