© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1554
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and their patterns

    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
    HasForeignKey
    -0.62
    PostMapping
    -0.61
    RequestMapping
    -0.56
    SpringBootTest
    -0.55
    arraycopy
    -0.53
    GEBURTSDATUM
    -0.52
    GetMapping
    -0.52
    WriteBarrier
    -0.51
    in
    -0.50
     including
    -0.50
    POSITIVE LOGITS
    enumi
    1.01
     виправивши
    0.98
    \{\\
    0.93
    érêt
    0.74
    +#+#
    0.73
    Skocz
    0.69
     تضيفلها
    0.69
    IUrlHelper
    0.68
    󠁴
    0.68
      (
    0.68
    Activations Density 0.378%

    No Known Activations