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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1796
    Prev
    Next
    INDEX
    Explanations

    instances of the word "track" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morley
    -0.75
    OLIC
    -0.74
     Maier
    -0.73
     Bolts
    -0.70
    SSM
    -0.70
    ngOnInit
    -0.69
    mle
    -0.66
     SSM
    -0.66
     Valeria
    -0.66
    மை
    -0.66
    POSITIVE LOGITS
     Track
    1.41
     tracks
    1.39
     Tracks
    1.38
     TRACK
    1.38
     track
    1.35
    Track
    1.27
    TRACK
    1.26
    track
    1.21
    tracks
    1.21
     trackers
    1.15
    Activations Density 0.069%

    No Known Activations