© 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. 39-GEMMASCOPE-RES-16K
    6. 3099
    Prev
    Next
    INDEX
    Explanations

    the act of looking or observing, particularly in a forward or anticipatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.47
    mobileqq
    -0.44
    ndag
    -0.41
     собою
    -0.41
    INCREF
    -0.40
    JNIEnv
    -0.38
    otry
    -0.37
    iredo
    -0.36
     TMPro
    -0.36
    oas
    -0.36
    POSITIVE LOGITS
     forward
    0.87
     closely
    0.69
    ahead
    0.66
     into
    0.65
    alike
    0.63
     FORWARD
    0.63
     Forward
    0.62
    forward
    0.61
     ahead
    0.60
    rungsseite
    0.59
    Activations Density 0.091%

    No Known Activations