© 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. 3118
    Prev
    Next
    INDEX
    Explanations

    terms associated with tight physical constraints or conditions

    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
    AndEndTag
    -0.52
    irvana
    -0.43
     ویکی‌پدی
    -0.41
     PyLong
    -0.40
    degna
    -0.37
     jadx
    -0.37
    évaluateur
    -0.37
    TargetException
    -0.36
    🖨
    -0.36
    copal
    -0.36
    POSITIVE LOGITS
     tight
    3.28
     Tight
    3.02
    Tight
    2.91
    tight
    2.84
     tighter
    2.81
     tighten
    2.59
     tightened
    2.56
     tightness
    2.55
     tightening
    2.42
     tightly
    2.38
    Activations Density 0.697%

    No Known Activations