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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11577
    Prev
    Next
    INDEX
    Explanations

    instances of the word "initial" and variations of its usage in the context of reports, assessments, or evaluations

    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
     enseña
    -0.64
     mesurer
    -0.63
    ToScroll
    -0.63
    chluss
    -0.59
     что
    -0.58
    frau
    -0.58
    Borg
    -0.57
     Foxx
    -0.57
    ى
    -0.56
    wo
    -0.55
    POSITIVE LOGITS
     initial
    2.06
    initial
    1.96
     Initial
    1.95
    Initial
    1.85
     INITIAL
    1.70
    INITIAL
    1.66
    setInitial
    1.66
     inicial
    1.60
     initiale
    1.49
     initially
    1.44
    Activations Density 0.051%

    No Known Activations