© 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. 10894
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or characteristics of various subjects

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

    identification or differentiation

    np_acts-logits-general · gemini-2.0-flash

    distinguishing features

    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
    PerformLayout
    -0.58
     متعلقه
    -0.56
    bewerken
    -0.53
    protoimpl
    -0.52
     المعيارى
    -0.52
     مشين
    -0.51
     الحره
    -0.51
    jsii
    -0.50
    ьаж
    -0.50
     CYTHON
    -0.50
    POSITIVE LOGITS
     distinguishable
    1.39
     distinguishing
    1.31
     distinguish
    1.27
     identifiable
    1.23
     recognizable
    1.22
     recognisable
    1.21
     identification
    1.13
     distinguishes
    1.12
     unmistakable
    1.11
     differentiate
    1.09
    Activations Density 0.575%

    No Known Activations