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. 16-GEMMASCOPE-RES-16K
    6. 165
    Prev
    Next
    INDEX
    Explanations

    the word "and" in various contexts

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

    "And" followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    and

    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
    ########.
    -0.63
    ::*;
    -0.63
    {};
    -0.54
    "";
    -0.54
     antaranya
    -0.54
     fign
    -0.53
    */;
    -0.52
    <bos>
    -0.52
    )();
    -0.52
    "};
    -0.52
    POSITIVE LOGITS
     without
    1.18
    without
    1.01
     with
    0.96
     WITHOUT
    0.95
     assuming
    0.90
     excluding
    0.87
     lacking
    0.85
     ohne
    0.84
     requiring
    0.84
     having
    0.82
    Activations Density 0.370%

    No Known Activations