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. 16-GEMMASCOPE-RES-16K
    6. 3164
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and delimiters in code snippets

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

    Opening parenthesis

    np_acts-logits-general · gemini-2.0-flash

    あの sentence

    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
     U
    -0.71
     V
    -0.67
     O
    -0.66
     E
    -0.64
     H
    -0.64
     R
    -0.64
     L
    -0.63
     and
    -0.62
     S
    -0.60
     P
    -0.60
    POSITIVE LOGITS
    IsContent
    1.13
     purpoſe
    1.10
     auroit
    1.09
    )]=
    1.07
    }}$\\
    1.06
    "]=
    1.06
     AssemblyCulture
    1.04
    Personendaten
    1.03
    GEBURTSDATUM
    1.02
    Personensuche
    1.01
    Activations Density 0.286%

    No Known Activations