© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6334
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate likelihood or probability

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

    "likely"

    np_acts-logits-general · gemini-2.0-flash

    likelihood or probability

    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
     BoxFit
    -0.62
     &___
    -0.59
     AssemblyTitle
    -0.58
     بيها
    -0.57
     TestBed
    -0.52
    SOUNDBITE
    -0.51
     Normdatei
    -0.50
    InSection
    -0.50
     BoxDecoration
    -0.50
    outSlope
    -0.50
    POSITIVE LOGITS
     likely
    1.77
     Likely
    1.66
    likely
    1.61
    Likely
    1.52
     likelihood
    1.19
     Likelihood
    1.17
    Likelihood
    1.16
     unlikely
    1.15
    likelihood
    1.06
     probable
    1.02
    Activations Density 0.180%

    No Known Activations