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. 9-GEMMASCOPE-RES-16K
    6. 15193
    Prev
    Next
    INDEX
    Explanations

    programming concepts and terminology, particularly related to data structures and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.68
    ,
    -0.59
    …
    -0.54
     (
    -0.53
    ’
    -0.52
    <eos>
    -0.51
    '
    -0.51
    ...
    -0.49
     "
    -0.49
    /
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    1.28
    WithIOException
    1.17
    AccessorTable
    1.15
    Vidite
    1.12
    StoryboardSegue
    1.08
    MigrationBuilder
    1.06
     تكبرها
    1.06
     esternos
    1.05
    Personensuche
    1.04
     مشين
    1.02
    Activations Density 0.989%

    No Known Activations