© 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. 9-GEMMASCOPE-RES-16K
    11. 7156
    Prev
    Next
    INDEX
    Explanations

    details about properties and their features

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

    before nouns or noun phrases

    np_acts-logits-general · gemini-2.0-flash

    elevators, jets, toys, study, libraries, entertainment

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    hluk
    -0.40
    "."
    -0.34
    mend
    -0.33
    VYMaps
    -0.33
    siye
    -0.32
    ↹
    -0.32
    ement
    -0.32
     abject
    -0.32
     Exposition
    -0.31
    Proceed
    -0.31
    POSITIVE LOGITS
    AddTagHelper
    0.51
     MainAxisSize
    0.49
     CreateTagHelper
    0.49
    AsUp
    0.49
     OFDb
    0.49
     Roskov
    0.48
    posedge
    0.47
     بيها
    0.46
    UpInside
    0.46
     Constitucional
    0.46
    Activations Density 0.341%

    No Known Activations