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. 2-GEMMASCOPE-RES-16K
    6. 4923
    Prev
    Next
    INDEX
    Explanations

    terms related to medical devices, particularly stents and their associated properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endwhile
    -0.68
    ($__
    -0.64
     ProtoMessage
    -0.63
    COUVER
    -0.56
    liothèque
    -0.56
     SIMBAD
    -0.55
     arşivlendi
    -0.55
    awtextra
    -0.54
    .)}
    -0.54
    intendent
    -0.53
    POSITIVE LOGITS
    ents
    0.90
    ent
    0.82
    ENT
    0.78
    ence
    0.78
    ente
    0.76
    ENTS
    0.73
    ish
    0.65
    ences
    0.64
    ENCE
    0.63
    ENCES
    0.62
    Activations Density 2.373%

    No Known Activations