© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6879
    Prev
    Next
    INDEX
    Explanations

    structured list items or references to citation notes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.56
     a
    -0.54
     
    -0.53
    the
    -0.53
    The
    -0.52
    </em>
    -0.51
    ‘
    -0.51
    2
    -0.51
     For
    -0.51
    </i>
    -0.50
    POSITIVE LOGITS
     propOrder
    1.35
    __':
    1.31
    __":
    1.28
     تانيه
    1.17
    ReusableCell
    1.17
     متعلقه
    1.10
     المعيارى
    1.10
    AndEndTag
    1.09
    tagHelperRunner
    1.07
    rungsseite
    1.06
    Activations Density 0.183%

    No Known Activations