© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5469
    Prev
    Next
    INDEX
    Explanations

    references to locations and structures tied to events or entities

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

    Preceding words before "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    pairs connected by and/or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.56
     Geiſt
    -0.53
    gorra
    -0.52
     étoient
    -0.52
    hoeddwyd
    -0.52
     ©️
    -0.49
    arky
    -0.49
    ]")]
    -0.49
     Geſch
    -0.48
    chengla
    -0.47
    POSITIVE LOGITS
     and
    0.46
     esternos
    0.45
    DebuggerNonUser
    0.45
    astéroïdes
    0.44
    abestanden
    0.42
    rungsseite
    0.35
    OGND
    0.35
     HasFactory
    0.34
    Reklama
    0.33
     CommonModule
    0.33
    Activations Density 0.563%

    No Known Activations