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. 14595
    Prev
    Next
    INDEX
    Explanations

    elements indicating the beginning of a new section or reference in text, such as headings or formatted tags

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

    First word of a sentence

    np_acts-logits-general · gemini-2.0-flash

    Working, Body, Mixing, Nick, import, Synthesis, McKin, Marie

    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
    Personensuche
    -0.76
    SourceChecksum
    -0.74
    ())))
    -0.68
    </strong>
    -0.66
    AddTagHelper
    -0.65
    millimeters
    -0.63
    ()))
    -0.59
    ))}
    -0.59
     chi̍t
    -0.59
    )\}
    -0.58
    POSITIVE LOGITS
    </i>
    0.99
    numerusform
    0.74
    </b>
    0.69
    InstrumentedTest
    0.64
    AndEndTag
    0.60
     محفوظة
    0.58
    writeField
    0.58
    erover
    0.54
    +:+
    0.52
     ElementRef
    0.51
    Activations Density 2.037%

    No Known Activations