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. 3-GEMMASCOPE-RES-16K
    6. 5971
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements, particularly closing brackets and specific formatting instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToTable
    -0.58
    %)$
    -0.58
     légales
    -0.57
    deoxy
    -0.56
     censi
    -0.56
     Eastwood
    -0.53
     symb
    -0.52
    ImageField
    -0.52
    endmodule
    -0.52
    ☂
    -0.51
    POSITIVE LOGITS
    WithIOException
    0.78
     }}$}
    0.73
    HasForeignKey
    0.73
    RegistryLite
    0.71
    Gön
    0.69
    Geplaatst
    0.69
    iastes
    0.68
    łożyć
    0.68
     SwitchCompat
    0.67
    帖最后由
    0.65
    Activations Density 0.101%

    No Known Activations