© 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. 24-GEMMASCOPE-RES-16K
    6. 16102
    Prev
    Next
    INDEX
    Explanations

    specific scientific methods and techniques related to processing biological samples

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

    preceding "using" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    laboratory separation and analysis methods

    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
    !—
    -0.68
     يتيمه
    -0.63
    getSeconds
    -0.62
    Especially
    -0.56
     nonUne
    -0.56
     själva
    -0.55
    !--
    -0.55
    endmodule
    -0.54
    ("="
    -0.53
    iseite
    -0.53
    POSITIVE LOGITS
     using
    1.27
     followed
    1.08
    using
    0.94
     following
    0.88
     prior
    0.85
     utilizzando
    0.85
     utilizando
    0.84
     employing
    0.83
    followed
    0.81
     USING
    0.79
    Activations Density 2.254%

    No Known Activations