© 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. 440
    Prev
    Next
    INDEX
    Explanations

    key-value pair structures in data

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

    "value"

    np_acts-logits-general · gemini-2.0-flash

    key value pair

    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
    GEBURTSDATUM
    -0.51
    UrlResolution
    -0.50
    ]")]
    -0.49
     Sarm
    -0.48
     cæ
    -0.48
    HomeAsUpEnabled
    -0.47
     corners
    -0.47
    elemField
    -0.47
     tank
    -0.47
    Становништво
    -0.46
    POSITIVE LOGITS
    ografija
    0.40
     defaultstate
    0.35
    Viki
    0.35
     explicación
    0.34
    respuesta
    0.34
    response
    0.33
     correspondiente
    0.32
    enterOuterAlt
    0.32
     desconocido
    0.32
    ForValue
    0.31
    Activations Density 0.906%

    No Known Activations