Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 8673
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and parameters related to handling options and configurations in a software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revanche
    -0.58
    ::_('
    -0.56
     `${
    -0.53
     دیکھیے
    -0.53
     restTemplate
    -0.51
    \}\\
    -0.50
    lacian
    -0.50
    brtc
    -0.49
    bula
    -0.49
     Muda
    -0.49
    POSITIVE LOGITS
     ||
    1.27
    ||
    1.11
     ||=
    0.82
     or
    0.76
     ||
    
    0.73
     ?:
    0.66
    getOr
    0.66
    |||
    0.63
    )||
    0.60
    '||
    0.60
    Activations Density 0.186%

    No Known Activations