© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15204
    Prev
    Next
    INDEX
    Explanations

    names that include the word "Hill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     STANFORD
    -0.49
     ser
    -0.48
     Forman
    -0.47
     Seok
    -0.46
    CHICAGO
    -0.46
     Solskjaer
    -0.46
     Bourgoin
    -0.46
     πα
    -0.45
    sko
    -0.44
     Quo
    -0.44
    POSITIVE LOGITS
     Hill
    4.19
     hill
    4.13
    Hill
    4.04
     HILL
    3.85
    hill
    3.42
    HILL
    3.10
     hills
    2.82
     Hills
    2.40
     hillside
    2.26
    hills
    2.22
    Activations Density 0.068%

    No Known Activations