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. 17-GEMMASCOPE-RES-16K
    6. 11444
    Prev
    Next
    INDEX
    Explanations

    references to tables and database structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    -0.82
    <em>
    -0.75
    on
    -0.72
    at
    -0.69
    and
    -0.68
    o
    -0.66
    a
    -0.64
    en
    -0.64
    ת
    -0.62
    u
    -0.62
    POSITIVE LOGITS
     виправивши
    1.29
     betweenstory
    1.27
    DockStyle
    1.23
    AddTagHelper
    1.09
    IsMutable
    1.07
    AccessorTable
    1.05
    kháu
    1.05
    WriteTagHelper
    1.04
    SerializedSize
    1.03
    thâu
    1.01
    Activations Density 1.177%

    No Known Activations