© 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. 13-GEMMASCOPE-RES-16K
    11. 7229
    Prev
    Next
    INDEX
    Explanations

    code structures, particularly related to functions and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    messageInfo
    -0.47
    IsMutable
    -0.46
     ModelRenderer
    -0.46
    setViewportView
    -0.45
    __':
    -0.45
    expandindo
    -0.44
     awakeFromNib
    -0.41
    saraba
    -0.40
     dieß
    -0.39
    "]();
    -0.39
    POSITIVE LOGITS
     onCreateView
    0.74
    #+#
    0.59
     compétence
    0.46
     pubblic
    0.45
     oscuros
    0.45
     templado
    0.44
    istic
    0.43
     nabíz
    0.43
     Autorizaciones
    0.43
     withheld
    0.42
    Activations Density 0.276%

    No Known Activations