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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 514
    Prev
    Next
    INDEX
    Explanations

    numeric values and structured data representations

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

    hexadecimal-style codes and memory/address dump entries in structured, code-like data.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dAtA
    -0.41
    новниш
    -0.41
     utafitiHapana
    -0.40
    GetAxis
    -0.40
     chi̍t
    -0.38
    __((
    -0.38
    lific
    -0.37
    
    -0.36
    cheer
    -0.35
    arraycopy
    -0.35
    POSITIVE LOGITS
    BeginContext
    0.60
    SourceChecksum
    0.52
    yntaxException
    0.52
    EClass
    0.48
    ToBounds
    0.47
    OGND
    0.47
     EconPapers
    0.47
    ↹
    0.47
     propOrder
    0.45
     disambiguazione
    0.45
    Activations Density 1.004%

    No Known Activations