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. 24-GEMMASCOPE-RES-16K
    6. 14225
    Prev
    Next
    INDEX
    Explanations

    numeric data or references in a scientific context

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

    Text preceding a citation or reference

    np_acts-logits-general · gemini-2.0-flash

    academic citations and references

    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
    ://$
    -0.52
     brauchst
    -0.50
    abetes
    -0.50
     solltest
    -0.48
    tableFuture
    -0.46
     enää
    -0.46
    -------
    -0.46
    verwijspagina
    -0.45
     kannst
    -0.45
     Anything
    -0.43
    POSITIVE LOGITS
     jScrollPane
    0.76
    SourceChecksum
    0.74
    doi
    0.72
     doi
    0.68
    bibitem
    0.65
    IUrlHelper
    0.65
    ORCID
    0.64
     papers
    0.63
    Received
    0.63
    Papers
    0.62
    Activations Density 0.390%

    No Known Activations