© 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. 25-GEMMASCOPE-RES-16K
    11. 15160
    Prev
    Next
    INDEX
    Explanations

    URLs related to GitHub raw content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setViewportView
    -0.51
    IBarButtonItem
    -0.49
    SequentialGroup
    -0.49
     المعيارى
    -0.48
    stdlib
    -0.45
    ⅘
    -0.45
    canti
    -0.44
     TRACK
    -0.44
     track
    -0.44
     bArr
    -0.44
    POSITIVE LOGITS
     <>",
    0.53
    UnusedPrivate
    0.42
    Sprintf
    0.41
     ***!
    0.40
    endcsname
    0.37
     anſ
    0.37
     itſelf
    0.35
     atas
    0.34
     raiſ
    0.34
     }}(\
    0.33
    Activations Density 0.068%

    No Known Activations