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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4307
    Prev
    Next
    INDEX
    Explanations

    discussions about competition and common elements in various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivores
    -0.37
     manches
    -0.37
    jäh
    -0.35
     klart
    -0.35
     Division
    -0.35
    entennial
    -0.35
    ichern
    -0.35
    (__('
    -0.35
    一分
    -0.34
    owska
    -0.33
    POSITIVE LOGITS
    AutoScaleMode
    1.19
    ArgsConstructor
    0.93
    rrggbb
    0.88
     дописавши
    0.87
     between
    0.86
    RegistryLite
    0.85
    rungsseite
    0.84
     AssemblyVersion
    0.83
    spaceBetween
    0.83
    StoryboardSegue
    0.83
    Activations Density 1.047%

    No Known Activations