© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13711
    Prev
    Next
    INDEX
    Explanations

    information related to titles of items, particularly in the context of media or database entries

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

    Items followed by colons or equals signs

    np_acts-logits-general · gemini-2.0-flash

    label followed by separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sulit
    -0.23
    dengar
    -0.23
     Gri
    -0.22
     only
    -0.21
     Jackson
    -0.21
    NewValue
    -0.21
     dark
    -0.20
     overcome
    -0.20
     keker
    -0.20
     podia
    -0.20
    POSITIVE LOGITS
    Personendaten
    0.86
     ModelExpression
    0.84
     AssemblyTitle
    0.84
    rungsseite
    0.82
    AutoScaleMode
    0.79
     name
    0.75
     이름
    0.74
    名称
    0.73
     utafitiHapana
    0.73
    WebElementEntity
    0.72
    Activations Density 0.452%

    No Known Activations