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. 1-GEMMASCOPE-RES-16K
    6. 9266
    Prev
    Next
    INDEX
    Explanations

    words related to specific properties or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.75
     Torna
    -0.60
     مرئيه
    -0.59
    ########.
    -0.58
     Normdatei
    -0.56
    CDCl
    -0.56
     Italijani
    -0.54
    Välislingid
    -0.53
     мәкал
    -0.53
    خصة
    -0.52
    POSITIVE LOGITS
    tic
    3.15
    TIC
    1.25
    Tic
    1.24
    ticum
    1.09
    ticity
    1.02
    tics
    0.99
    ETIC
    0.94
     tic
    0.91
     Tic
    0.89
    tică
    0.87
    Activations Density 0.062%

    No Known Activations