© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8562
    Prev
    Next
    INDEX
    Explanations

    instances of examples and case references

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

    Examples and instances

    np_acts-logits-general · gemini-2.0-flash

    as an example

    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
    MigrationBuilder
    -0.41
    Зноскі
    -0.37
     doInBackground
    -0.34
    よいよ
    -0.33
    ſts
    -0.31
    qvarna
    -0.31
     turísticos
    -0.31
     detailsNormal
    -0.30
    lewati
    -0.30
    AutoModerator
    -0.30
    POSITIVE LOGITS
     example
    3.25
     examples
    2.97
    example
    2.70
     Examples
    2.67
     Example
    2.67
    Example
    2.61
     ejemplo
    2.58
     exemples
    2.56
    Examples
    2.52
     Beispiel
    2.48
    Activations Density 1.102%

    No Known Activations