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. 24-GEMMASCOPE-RES-16K
    6. 12748
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to microscopy and imaging techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "of", "a", or "the" followed by optical instruments

    np_acts-logits-general · gemini-2.0-flash

    scopes, binoculars, and optical devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.59
     Pank
    -0.58
    RenderAtEndOf
    -0.58
     utafitiHapana
    -0.56
    DatabaseError
    -0.54
    BeginContext
    -0.53
    bootstrapcdn
    -0.51
    AccessorTable
    -0.51
    \{\\
    -0.49
    NullException
    -0.48
    POSITIVE LOGITS
     scope
    1.20
     scopes
    1.17
    scope
    1.04
     binoculars
    1.02
     magnification
    1.00
     Scope
    0.99
    scopes
    0.96
     ey
    0.94
    Scope
    0.92
     ocular
    0.90
    Activations Density 0.143%

    No Known Activations