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. 6705
    Prev
    Next
    INDEX
    Explanations

    performance metrics related to sports statistics

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

    Numbers followed by game/pass related words

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by game statistics

    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
    RetentionPolicy
    -0.77
    
    -0.74
    )}</
    -0.58
     CanadaChoose
    -0.58
    twimg
    -0.57
    WebControls
    -0.56
    fromCharCode
    -0.54
    XmlEnum
    -0.54
    #+#
    -0.53
    enumii
    -0.53
    POSITIVE LOGITS
     otomatig
    0.63
     tests
    0.55
     sampled
    0.54
     sampling
    0.51
     test
    0.51
     biopsy
    0.51
    diğinde
    0.51
    sampled
    0.50
     attempt
    0.49
     biopsies
    0.48
    Activations Density 0.292%

    No Known Activations