© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12488
    Prev
    Next
    INDEX
    Explanations

    discussions about personal experiences and emotional reflections

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

    Sentences starting with "I" or personal narratives

    np_acts-logits-general · gemini-2.0-flash

    recently started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]');
    -0.61
    Ữ
    -0.56
     yourself
    -0.55
     yourselves
    -0.54
     you
    -0.54
    gdx
    -0.53
     youll
    -0.53
    ]");
    -0.53
    )";
    -0.53
     jäl
    -0.52
    POSITIVE LOGITS
     Lately
    1.45
     Recently
    1.45
    Recently
    1.42
     lately
    1.34
     recently
    1.32
    Last
    1.32
     Last
    1.27
    recently
    1.23
     last
    1.22
     recentemente
    1.09
    Activations Density 0.292%

    No Known Activations