© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14947
    Prev
    Next
    INDEX
    Explanations

    repeated phrases and synonyms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    c
    -0.77
    ly
    -0.76
    ni
    -0.75
    tic
    -0.75
    nik
    -0.74
    len
    -0.71
     Khat
    -0.70
    Phi
    -0.69
    nin
    -0.69
    rio
    -0.69
    POSITIVE LOGITS
    кож
    1.21
    RegistryLite
    1.20
    ALSO
    1.13
    wnież
    1.09
     ALSO
    1.07
    gså
    1.06
    ępnie
    1.05
     Também
    1.05
     Normdatei
    1.05
    omiast
    1.03
    Activations Density 0.135%

    No Known Activations