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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 1337
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "hook" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.94
     Majefty
    -0.87
    aarrggbb
    -0.81
     poffible
    -0.79
    djangoproject
    -0.79
    viewDidLoad
    -0.78
     Sterne
    -0.78
     ftate
    -0.78
    readAs
    -0.75
     GenerationType
    -0.75
    POSITIVE LOGITS
     hooks
    2.67
     hook
    2.66
     HOOK
    2.57
     Hook
    2.51
     Hooks
    2.43
    hook
    2.42
    Hook
    2.39
    hooks
    2.31
     hooked
    2.26
     hooking
    2.25
    Activations Density 0.034%

    No Known Activations