© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1109
    Prev
    Next
    INDEX
    Explanations

    phrases related to tying or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "tie" or "tying"

    np_acts-logits-general · gemini-2.0-flash

    tying and knots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lecteur
    -0.64
    ötzlich
    -0.64
    </s>
    -0.63
     poch
    -0.63
    🏻‍♀️
    -0.63
    ഴ
    -0.61
     Shells
    -0.59
    幕
    -0.58
    millan
    -0.57
     Bedrock
    -0.57
    POSITIVE LOGITS
     tying
    1.32
     ties
    1.32
     tie
    1.31
     tied
    1.30
     knots
    1.28
     Ties
    1.27
     Tie
    1.27
     Knot
    1.15
     knot
    1.15
    knot
    1.13
    Activations Density 0.139%

    No Known Activations