© 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. 16-GEMMASCOPE-RES-16K
    6. 9203
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical terms related to programming and equations

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

    after named entities or titles

    np_acts-logits-general · gemini-2.0-flash

    specific dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.33
     becauſe
    -1.17
     purpoſe
    -1.14
     houſe
    -1.13
    ſelf
    -1.13
     uſed
    -1.12
     صوتيه
    -1.12
     myſelf
    -1.12
     ―――――
    -1.10
    +#+#
    -1.10
    POSITIVE LOGITS
    <eos>
    0.63
    <bos>
    0.53
    .
    0.47
     in
    0.46
    ↵
    0.43
    ↵↵↵
    0.42
    -
    0.42
     :
    0.42
     de
    0.41
    ,
    0.39
    Activations Density 0.655%

    No Known Activations