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. 4-GEMMASCOPE-RES-16K
    6. 11140
    Prev
    Next
    INDEX
    Explanations

    phrases related to representation and accuracy in data sampling and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.59
    aternion
    -0.52
     cincin
    -0.49
    übt
    -0.49
    chlag
    -0.48
    ariable
    -0.46
    зня
    -0.46
    accessory
    -0.46
    ometries
    -0.46
     nakalista
    -0.45
    POSITIVE LOGITS
    AnchorStyles
    0.85
     representative
    0.82
     representation
    0.80
     snapshot
    0.75
     REPRESENT
    0.74
     Representation
    0.73
    representative
    0.73
    Representation
    0.71
    representation
    0.70
     snapshots
    0.68
    Activations Density 1.057%

    No Known Activations