© 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. 2103
    Prev
    Next
    INDEX
    Explanations

    structured items related to biological and product properties

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

    shape

    np_acts-logits-general · gemini-2.0-flash

    shapes and resemblance

    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
     vocales
    -0.32
    engager
    -0.32
    معلومات
    -0.31
    engagent
    -0.30
    ::*;
    -0.29
     bParam
    -0.28
     yarar
    -0.27
    μως
    -0.27
    Datetime
    -0.27
     konserv
    -0.27
    POSITIVE LOGITS
     triangular
    0.79
     resembles
    0.74
     rectangular
    0.71
    awtextra
    0.71
     resembling
    0.71
     betweenstory
    0.69
     resemble
    0.69
     resembled
    0.68
     rounded
    0.66
     circular
    0.65
    Activations Density 0.478%

    No Known Activations