© 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. 30-GEMMASCOPE-RES-16K
    11. 11043
    Prev
    Next
    INDEX
    Explanations

    concepts related to analysis and evaluation techniques

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

    Tokens introducing sections or steps

    np_acts-logits-general · gemini-2.0-flash

    dose of methadone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.45
     latter
    -0.43
    Véxase
    -0.40
    Šaltiniai
    -0.36
     więc
    -0.36
    이며
    -0.36
     berupa
    -0.31
     njego
    -0.31
     mismas
    -0.30
     deren
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.92
    SequentialGroup
    0.83
    ✭✭
    0.72
    enderror
    0.68
    
    0.65
    ApiModelProperty
    0.63
    Personendaten
    0.63
    tonode
    0.63
    AddTagHelper
    0.63
     Although
    0.62
    Activations Density 0.923%

    No Known Activations