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. 6-GEMMASCOPE-RES-16K
    6. 6077
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to patient outcomes and clinical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.85
     Daarom
    -0.79
    ſelves
    -0.71
     Diſ
    -0.70
     Majefty
    -0.70
     greateſt
    -0.68
    ſelf
    -0.67
    ViewFeatures
    -0.66
    +#+#
    -0.66
     Eſ
    -0.66
    POSITIVE LOGITS
     others
    0.65
     (
    0.55
     da
    0.53
    Others
    0.51
     Others
    0.51
     minor
    0.48
     from
    0.48
     davon
    0.47
     other
    0.47
     of
    0.47
    Activations Density 0.852%

    No Known Activations