© 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. 10768
    Prev
    Next
    INDEX
    Explanations

    pronouns, particularly "it" and "there," indicating a focus on references and existential statements 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 @ 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
    brainly
    -0.77
     photolibrary
    -0.72
    MLLoader
    -0.71
     doubtnut
    -0.70
    haustible
    -0.70
    decoración
    -0.69
    /*
    -0.69
     chociaż
    -0.68
     Shakspeare
    -0.67
     publick
    -0.66
    POSITIVE LOGITS
    for
    0.65
    which
    0.64
    but
    0.60
    we
    0.59
    in
    0.59
    so
    0.59
    cu
    0.58
    not
    0.56
     Италијани
    0.55
    more
    0.55
    Activations Density 0.237%

    No Known Activations