Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6672
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "th" associated with various numerical contexts, specifically relating to sequences or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.61
    \{\\
    -0.61
    astify
    -0.60
    पया
    -0.59
    softc
    -0.58
    PerformLayout
    -0.57
    Clare
    -0.57
    arcs
    -0.56
    cupertino
    -0.56
    __":
    
    -0.56
    POSITIVE LOGITS
     fifth
    1.16
    th
    1.14
     Fifth
    1.09
     third
    1.09
     sixth
    1.08
    Fifth
    1.05
     seventh
    1.05
     ninth
    1.03
     Third
    1.02
     fourth
    1.02
    Activations Density 0.180%

    No Known Activations