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. 8140
    Prev
    Next
    INDEX
    Explanations

    elements related to references and citations, particularly in a scientific or academic context

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

    Text citations

    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
     ExecuteAsync
    -0.70
    parsedMessage
    -0.70
    SequentialGroup
    -0.65
    ReusableCell
    -0.59
     AssemblyVersion
    -0.59
    >*/
    -0.56
    liothèque
    -0.54
    ))$
    -0.53
    }}$\\
    -0.53
    webElement
    -0.51
    POSITIVE LOGITS
    cite
    0.74
    ref
    0.65
     cite
    0.57
    asteroide
    0.57
    енча
    0.56
     cited
    0.56
     refs
    0.55
     Ref
    0.55
    citep
    0.54
    Източници
    0.54
    Activations Density 1.851%

    No Known Activations