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. 10032
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and API specifications

    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
     nakalista
    -0.91
    SBATCH
    -0.81
    WriteBarrier
    -0.70
    rungsseite
    -0.65
     onAnimation
    -0.61
     púb
    -0.61
    />";
    -0.61
     }}"></
    -0.60
     pretext
    -0.60
    Izvori
    -0.60
    POSITIVE LOGITS
    lexikon
    0.53
     ::
    0.51
    RegistryLite
    0.48
    RectangleBorder
    0.48
    (::
    0.46
    tsch
    0.46
    Diweddarwch
    0.45
    rie
    0.44
    SourceChecksum
    0.44
    SessionFactory
    0.44
    Activations Density 0.380%

    No Known Activations