© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11394
    Prev
    Next
    INDEX
    Explanations

    key points and descriptors related to image processing and detection metrics

    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
     
    -0.46
     h
    -0.36
    底
    -0.35
     At
    -0.35
     kep
    -0.34
    at
    -0.34
     at
    -0.34
    ж
    -0.34
     trasp
    -0.34
    žd
    -0.34
    POSITIVE LOGITS
     CreateTagHelper
    1.34
     autorytatywna
    1.18
    __*/
    1.13
     ProtoMessage
    1.12
    TagMode
    1.08
    rrggbb
    1.08
    +#+#
    1.08
    ollectionView
    1.06
    MigrationBuilder
    1.04
     متعلقه
    1.03
    Activations Density 1.614%

    No Known Activations