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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 8921
    Prev
    Next
    INDEX
    Explanations

    bits of code related to error handling and logging mechanics in a programming context

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

    Code snippets containing "with"

    np_acts-logits-general · gemini-2.0-flash

    and RNA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.83
    abestanden
    -0.70
    DeleteBehavior
    -0.65
    CloseOperation
    -0.59
    ={`${
    -0.58
    RestController
    -0.56
    AccessorTable
    -0.56
     Elek
    -0.55
    ContentAlignment
    -0.55
    TypedDataSet
    -0.55
    POSITIVE LOGITS
     lenker
    0.71
    yszer
    0.52
    xase
    0.49
    Дереккөздер
    0.49
    mockMvc
    0.48
     nope
    0.48
    нциклопедия
    0.47
     behövs
    0.47
    tovers
    0.47
    inigungs
    0.47
    Activations Density 0.037%

    No Known Activations