© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2582
    Prev
    Next
    INDEX
    Explanations

    information about the release history and details of music albums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assigning
    -0.53
     PhpStorm
    -0.47
    assign
    -0.47
     Assign
    -0.46
     assign
    -0.46
    erg
    -0.45
    ﴿
    -0.45
    viro
    -0.45
    ädie
    -0.45
    Singing
    -0.45
    POSITIVE LOGITS
     album
    1.36
     albums
    1.16
    album
    1.05
     EP
    0.98
     Album
    0.97
     álbum
    0.93
     release
    0.92
     ALBUM
    0.92
    Album
    0.90
     typelib
    0.88
    Activations Density 0.122%

    No Known Activations