© 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. 0-GEMMASCOPE-RES-16K
    6. 3018
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions or qualities associated with tightness and looseness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtre
    -0.61
     ſta
    -0.60
     faſt
    -0.59
     purpoſe
    -0.52
     reaſon
    -0.50
     myſelf
    -0.50
     beſ
    -0.49
     pleaſure
    -0.48
     ſte
    -0.48
     ſever
    -0.47
    POSITIVE LOGITS
    loose
    0.66
    tight
    0.66
     Tight
    0.64
     eg
    0.63
    Tight
    0.62
    eg
    0.59
     tight
    0.58
    blockchain
    0.57
     tighten
    0.56
    Loose
    0.56
    Activations Density 0.285%

    No Known Activations