© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15929
    Prev
    Next
    INDEX
    Explanations

    references to documents and file types associated with research data

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

    file size specifications and document format indicators.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.58
     незавершена
    -0.54
    /*---
    -0.49
    CodeAttribute
    -0.46
    日閲覧
    -0.45
    bitField
    -0.43
    cuta
    -0.43
     !”
    -0.42
    inWeight
    -0.41
     didst
    -0.41
    POSITIVE LOGITS
    #+#
    0.55
    Datuak
    0.54
    canestro
    0.50
    oarece
    0.47
    WriteBarrier
    0.40
     redondo
    0.40
     препратки
    0.40
     أعلام
    0.39
    therosclerosis
    0.39
    amitié
    0.39
    Activations Density 0.916%

    No Known Activations