© 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. 5-GEMMASCOPE-RES-16K
    6. 10775
    Prev
    Next
    INDEX
    Explanations

    references to forests and forest-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -1.13
     estekak
    -1.04
     تضيفلها
    -1.03
    adaptiveStyles
    -1.02
    tonsoft
    -1.02
    featureID
    -1.00
    IBarButtonItem
    -0.99
    LabelTagHelper
    -0.98
     ainfi
    -0.98
     Viceroy
    -0.98
    POSITIVE LOGITS
     forest
    2.23
     Forest
    2.08
    forest
    1.96
    Forest
    1.92
     forests
    1.71
     FOREST
    1.60
    FOREST
    1.52
     Forests
    1.42
     Forrest
    1.33
    Forrest
    1.26
    Activations Density 0.045%

    No Known Activations