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. 4-GEMMASCOPE-RES-16K
    6. 394
    Prev
    Next
    INDEX
    Explanations

    greetings or salutations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nestjs
    -0.71
    WEBPACK
    -0.70
    FieldDescriptor
    -0.67
     borg
    -0.63
    Feld
    -0.62
    onde
    -0.61
    Xna
    -0.61
    голь
    -0.61
    naie
    -0.60
    Orléans
    -0.60
    POSITIVE LOGITS
    Hi
    2.22
     Hi
    2.19
     hi
    1.87
    hi
    1.73
     HI
    1.49
    HI
    1.46
     Hiram
    1.30
     Hira
    1.20
     Hipp
    1.19
    Hiya
    1.11
    Activations Density 0.047%

    No Known Activations