Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10426
    Prev
    Next
    INDEX
    Explanations

    instances of the word "information" and its related concepts

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

    followed by a verb "is," "does," or "was."

    np_acts-logits-general · gemini-2.0-flash

    This [noun] [verb of being/doing]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.79
     this
    -0.79
    OGND
    -0.74
    this
    -0.73
     Administrativna
    -0.71
    yntaxException
    -0.69
     цього
    -0.66
    uxxxx
    -0.66
     этого
    -0.65
    WriteAttribute
    -0.64
    POSITIVE LOGITS
     alone
    0.70
     also
    0.54
     nämlich
    0.54
     ALONE
    0.53
     together
    0.53
    一出
    0.52
    แห
    0.52
     específico
    0.51
     however
    0.51
     soort
    0.51
    Activations Density 0.545%

    No Known Activations