© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11477
    Prev
    Next
    INDEX
    Explanations

    references to citations or sources in the text

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

    that start with "Ref" or "reference"

    np_acts-logits-general · gemini-2.0-flash

    reference or ref followed by colon or hyphen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    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
    -0.65
     considérons
    -0.64
     viewDidLoad
    -0.59
     CreateTagHelper
    -0.58
    utives
    -0.57
     Drapeau
    -0.57
     Himo
    -0.57
    DataPropertyName
    -0.56
    UserScript
    -0.55
    enterOuterAlt
    -0.54
    POSITIVE LOGITS
     Ref
    0.81
     reference
    0.81
    ref
    0.81
     ref
    0.80
     refer
    0.79
     Refer
    0.78
     Reference
    0.77
    Ref
    0.76
    Refer
    0.72
    Reference
    0.71
    Activations Density 0.422%

    No Known Activations