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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 16030
    Prev
    Next
    INDEX
    Explanations

    numeric sequences or values, particularly in a structured format

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

    Numbers, sometimes followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    legal citations and numbers

    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
    Identyfik
    -0.75
    esez
    -0.66
    Personensuche
    -0.59
    Autoritní
    -0.58
    ज़
    -0.58
    AddTagHelper
    -0.56
    RTLD
    -0.56
     كومونز
    -0.56
     guangdong
    -0.55
    hoeddwyd
    -0.54
    POSITIVE LOGITS
     passim
    0.81
    ValueStyle
    0.74
     bezit
    0.59
     verdient
    0.57
     citada
    0.55
     متعلقه
    0.53
     Administrativna
    0.51
     henvisninger
    0.49
     pgs
    0.47
    bcryptjs
    0.47
    Activations Density 0.086%

    No Known Activations