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. 18-GEMMASCOPE-RES-16K
    6. 14979
    Prev
    Next
    INDEX
    Explanations

    instances of the word "let" and its variations indicating permission or allowance

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

    Followed by "know" or "go"

    np_acts-logits-general · gemini-2.0-flash

    letting people know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Composable
    -0.55
     LoggerFactory
    -0.55
     pidiendo
    -0.48
     ***!
    -0.47
    obedience
    -0.47
    läng
    -0.46
    eradish
    -0.46
    SHO
    -0.45
     obeying
    -0.45
     chod
    -0.45
    POSITIVE LOGITS
     initComponents
    0.78
     ProtoMessage
    0.72
     slip
    0.70
    UserScript
    0.70
    KommentareTeilen
    0.68
     slide
    0.66
    principalColumn
    0.65
     متعلقه
    0.63
     تضيفلها
    0.62
     go
    0.62
    Activations Density 0.157%

    No Known Activations