© 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. 31-GEMMASCOPE-RES-16K
    11. 16170
    Prev
    Next
    INDEX
    Explanations

    citations and references in academic texts

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

    citation references and numerical citations in brackets.

    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
     betweenstory
    -0.72
     uſed
    -0.66
    Становништво
    -0.60
    Попис
    -0.59
    WebElementEntity
    -0.56
     raiſ
    -0.51
     Infórmanos
    -0.51
    HideFlags
    -0.50
    webElementXpaths
    -0.50
    WriteBarrier
    -0.50
    POSITIVE LOGITS
    polis
    0.42
    oph
    0.40
    med
    0.37
    idio
    0.36
     ujednoznacz
    0.35
    alu
    0.35
    ApiModel
    0.34
    issy
    0.34
    2
    0.34
    6
    0.34
    Activations Density 0.308%

    No Known Activations