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. 9126
    Prev
    Next
    INDEX
    Explanations

    phrases associated with reaching or connection

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

    "Reach" or "reaching" variations

    np_acts-logits-general · gemini-2.0-flash

    reaching or arriving at an outcome

    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
    esModule
    -0.66
    omenclature
    -0.62
     Chwiliwch
    -0.56
    nestjs
    -0.56
    bolista
    -0.56
    Allo
    -0.55
    Ciri
    -0.54
    Gid
    -0.54
     mn
    -0.53
    MRP
    -0.52
    POSITIVE LOGITS
     Reach
    1.30
     reached
    1.27
     reach
    1.26
     reaches
    1.24
    Reaching
    1.21
    reached
    1.20
     Reaching
    1.17
    reach
    1.17
    Reach
    1.16
    REACH
    1.12
    Activations Density 0.061%

    No Known Activations