© 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. 3-GEMMASCOPE-RES-16K
    6. 6331
    Prev
    Next
    INDEX
    Explanations

    numeric values and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.38
     ***!
    -0.31
     meisjes
    -0.30
    học
    -0.29
     retirado
    -0.29
    ])))
    -0.29
     ház
    -0.29
     indruk
    -0.29
     ChromeDriver
    -0.29
    Numerade
    -0.29
    POSITIVE LOGITS
    utilisons
    0.66
     Noon
    0.64
     noon
    0.63
    Noon
    0.63
    canestro
    0.59
     afternoon
    0.58
    Rptr
    0.57
    noon
    0.56
     Afternoon
    0.55
    Afternoon
    0.55
    Activations Density 0.212%

    No Known Activations