© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10593
    Prev
    Next
    INDEX
    Explanations

    references to object-oriented programming concepts, specifically identifiers like 'self' and 'super'

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

    Immediately before attributes/properties

    np_acts-logits-general · gemini-2.0-flash

    specific keywords after a turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.78
    OGND
    -0.74
     autorytatywna
    -0.74
     ब्रेकडाउन
    -0.73
    QMetaType
    -0.72
    Autoritní
    -0.69
     Италијани
    -0.69
    AddTagHelper
    -0.68
     OMITBAD
    -0.67
     ErrIntOverflow
    -0.67
    POSITIVE LOGITS
     voici
    0.38
    The
    0.36
    .
    0.35
    -
    0.33
    нцип
    0.33
     Consejo
    0.32
     продви
    0.32
     
    0.31
    AddWithValue
    0.31
    Master
    0.31
    Activations Density 0.063%

    No Known Activations