© 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. 1-GEMMASCOPE-RES-16K
    6. 2788
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.44
     gynhyrchwyd
    -0.42
    <?
    -0.40
     &___
    -0.40
     beginnetje
    -0.38
     rejected
    -0.36
     initState
    -0.36
    Espèce
    -0.36
    XmlEnum
    -0.35
    hdys
    -0.35
    POSITIVE LOGITS
     can
    2.80
    Can
    1.91
     Can
    1.88
     können
    1.80
    可以
    1.80
    can
    1.80
     pouvez
    1.74
     можно
    1.68
     kann
    1.66
     pouvons
    1.63
    Activations Density 0.243%

    No Known Activations