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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5510
    Prev
    Next
    INDEX
    Explanations

    the presence of the suffix "er" in various contexts, indicating a focus on agentive nouns or comparative adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     సౌకర్య
    -0.60
    RenderAtEndOf
    -0.60
    assertNull
    -0.60
    rzost
    -0.60
    ASTIC
    -0.59
     Lightfoot
    -0.58
    anguard
    -0.58
    migrationBuilder
    -0.58
    lietta
    -0.58
    miyorum
    -0.57
    POSITIVE LOGITS
    er
    3.34
    ER
    2.62
    ers
    1.96
    erer
    1.49
    erk
    1.48
    erle
    1.47
    erin
    1.46
    erli
    1.41
    eric
    1.41
    erate
    1.39
    Activations Density 0.226%

    No Known Activations