© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8961
    Prev
    Next
    INDEX
    Explanations

    references to protocols or programs related to genetic testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.44
    brate
    -0.36
    Joel
    -0.36
    ficial
    -0.36
    tagne
    -0.36
    ۜ
    -0.35
    StoreMessageInfo
    -0.35
     mercancías
    -0.35
     malades
    -0.35
    BeginContext
    -0.35
    POSITIVE LOGITS
    pp
    3.69
    PP
    2.70
     pp
    2.70
     PP
    2.52
    Pp
    1.91
     Pp
    1.83
    pps
    1.63
    ppig
    1.52
    пп
    1.39
    ppi
    1.38
    Activations Density 0.287%

    No Known Activations