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. 4-GEMMASCOPE-RES-16K
    6. 3178
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and methodologies related to research and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icamente
    -0.61
    лактика
    -0.48
    ượng
    -0.48
    עת
    -0.47
     te
    -0.46
    angnya
    -0.46
     enf
    -0.46
     kid
    -0.45
    ugia
    -0.45
    sello
    -0.44
    POSITIVE LOGITS
     &
    1.12
    &
    1.06
     виправивши
    1.03
     \&
    1.00
    NewUrlParser
    0.95
    NameInMap
    0.91
    #+#
    0.87
    oredCriteria
    0.85
     Roskov
    0.85
     estekak
    0.84
    Activations Density 8.564%

    No Known Activations