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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 5950
    Prev
    Next
    INDEX
    Explanations

    positive descriptions and acknowledgments of services or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :+:
    -0.66
    });*/
    -0.64
    __))
    -0.63
    wps
    -0.57
    initComponents
    -0.56
     مشروع
    -0.54
    ⎧
    -0.54
    #+#
    -0.54
    etype
    -0.53
     material
    -0.53
    POSITIVE LOGITS
    interopRequire
    0.53
    łat
    0.53
     Viator
    0.52
     AttributeSet
    0.50
     públicas
    0.49
     humaines
    0.49
     препратки
    0.49
     دیکھیے
    0.48
    JsonHelper
    0.48
    pegno
    0.48
    Activations Density 0.073%

    No Known Activations