© 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. 22-GEMMASCOPE-RES-16K
    6. 2988
    Prev
    Next
    INDEX
    Explanations

    references to scientific methods or findings related to health and medical research

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

    Lists and numbered items

    np_acts-logits-general · gemini-2.0-flash

    first numbered item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -1.24
     rd
    -0.99
    RD
    -0.98
    +#+#
    -0.96
    Personendaten
    -0.88
     RD
    -0.88
    rds
    -0.81
    MessageTagHelper
    -0.77
    enumi
    -0.75
    enumii
    -0.72
    POSITIVE LOGITS
    st
    1.00
     st
    0.72
    ST
    0.71
     St
    0.58
    St
    0.58
    stl
    0.57
     sti
    0.56
     ST
    0.55
    ist
    0.53
     rest
    0.49
    Activations Density 0.330%

    No Known Activations