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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12337
    Prev
    Next
    INDEX
    Explanations

    reporting verbs that indicate actions or claims

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

    Past tense verbs; reports or claims

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs

    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
     pleaſure
    -0.64
     houſe
    -0.60
     ſtate
    -0.55
     ſche
    -0.51
     Houſe
    -0.51
     ſtre
    -0.50
    ChildScrollView
    -0.50
     endblock
    -0.48
    fören
    -0.48
    ſelf
    -0.47
    POSITIVE LOGITS
    ized
    0.69
    ched
    0.68
    iked
    0.68
    unked
    0.65
    ened
    0.65
    ted
    0.65
    pped
    0.63
    haped
    0.63
    vented
    0.63
    ourced
    0.63
    Activations Density 0.825%

    No Known Activations