© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4203
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating depth or intensity of experience, emotion, or analysis

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

    "deep" or its variations

    np_acts-logits-general · gemini-2.0-flash

    deep contexts and extents

    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
     autorytatywna
    -0.82
    帖最后由
    -0.74
     AssemblyCompany
    -0.72
    WebElementEntity
    -0.70
    LookAnd
    -0.67
    delwed
    -0.66
    oredCriteria
    -0.66
     onPostExecute
    -0.65
     Administrativna
    -0.64
    SBATCH
    -0.63
    POSITIVE LOGITS
     deep
    1.36
     Deep
    1.25
    deep
    1.21
     DEEP
    1.19
    Deep
    1.16
     depth
    1.13
     deeper
    1.12
    depth
    1.08
     deeply
    1.05
     deepest
    1.05
    Activations Density 0.123%

    No Known Activations