© 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. 2-GEMMASCOPE-RES-16K
    6. 730
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic coding and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hidupan
    -0.49
    parseColor
    -0.46
    ...
    -0.45
    UrlResolution
    -0.43
     rencontr
    -0.43
    tabular
    -0.42
     uncin
    -0.41
    setPassword
    -0.41
    setInput
    -0.40
    I
    -0.40
    POSITIVE LOGITS
     GS
    1.46
     GV
    1.40
     GSC
    1.33
     GSP
    1.26
     gc
    1.25
     GD
    1.24
     Gund
    1.23
     GA
    1.23
     GG
    1.23
     GES
    1.23
    Activations Density 3.848%

    No Known Activations