© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8458
    Prev
    Next
    INDEX
    Explanations

    instances of shared characteristics or commonalities among subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Common" or "shared" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    common or shared concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.41
     مشين
    -0.39
    BeginInit
    -0.37
    RTDA
    -0.36
    wapV
    -0.36
    ksamkeit
    -0.35
    vas
    -0.34
     Replica
    -0.34
    __':
    -0.34
    __":
    -0.33
    POSITIVE LOGITS
     common
    1.72
     shared
    1.66
    common
    1.49
    共通
    1.43
    shared
    1.39
     Shared
    1.36
    Shared
    1.30
     Common
    1.27
     COMMON
    1.27
    Common
    1.26
    Activations Density 0.553%

    No Known Activations