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. 14105
    Prev
    Next
    INDEX
    Explanations

    legal principles and references to rules or standards that should be applied in various contexts

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

    Following a rule, statement, or analysis

    np_acts-logits-general · gemini-2.0-flash

    application of rules or statements

    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
     typelib
    -0.58
     rhestr
    -0.56
     referenties
    -0.53
    IZON
    -0.50
    /**
    -0.47
    terase
    -0.47
    ждается
    -0.46
    TypedDataSet
    -0.46
     Fü
    -0.46
    ★★★★☆
    -0.45
    POSITIVE LOGITS
     apply
    2.56
     applies
    2.54
    apply
    2.14
     Apply
    2.08
     Applies
    2.04
    Apply
    2.00
     APPLY
    1.88
     applied
    1.87
     applying
    1.82
    Applies
    1.67
    Activations Density 0.667%

    No Known Activations