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. 17-GEMMASCOPE-RES-16K
    6. 1176
    Prev
    Next
    INDEX
    Explanations

    functions related to user interface components in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []:
    -0.50
    jelent
    -0.43
    BoxShadow
    -0.42
    COUVER
    -0.41
    ؤية
    -0.41
    ########.
    -0.40
     يتيمه
    -0.40
    kmale
    -0.40
    apia
    -0.40
    thian
    -0.39
    POSITIVE LOGITS
     resourceCulture
    0.68
    triangleq
    0.64
     microcontroller
    0.62
     purpoſe
    0.60
     itſelf
    0.59
    PyTuple
    0.59
    MessageTagHelper
    0.58
     isInitialized
    0.57
     Италијани
    0.57
     myſelf
    0.56
    Activations Density 0.496%

    No Known Activations