© 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. 18-GEMMASCOPE-RES-16K
    6. 14211
    Prev
    Next
    INDEX
    Explanations

    references to healthcare and medical professionals

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

    Follows punctuation or non-alphanumeric characters

    np_acts-logits-general · gemini-2.0-flash

    Latin roots and endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.97
    expandindo
    -0.78
    ValueStyle
    -0.75
     '\\;'
    -0.68
    Chham
    -0.65
     tartalomajánló
    -0.63
    adpleegd
    -0.63
     Bioaccumulative
    -0.60
     Roskov
    -0.60
    ServletConfig
    -0.58
    POSITIVE LOGITS
    </strong>
    2.85
    </b>
    2.45
    </u>
    2.34
    </em>
    2.21
    </h2>
    2.09
    </i>
    1.82
    </h4>
    1.78
    </code>
    1.73
    </h3>
    1.71
    </h5>
    1.45
    Activations Density 1.452%

    No Known Activations