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. 24-GEMMASCOPE-RES-16K
    6. 4965
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "affect" and its variations in different contexts

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

    following "af" or "aff"

    np_acts-logits-general · gemini-2.0-flash

    aff/aff followed by various endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.86
     mergeFrom
    -0.68
     pinulongan
    -0.67
    LabelTagHelper
    -0.65
    oredCriteria
    -0.63
    ConstraintMaker
    -0.60
    $_['
    -0.60
    EndContext
    -0.59
    AccessorTable
    -0.59
    ClientSize
    -0.58
    POSITIVE LOGITS
    cionados
    0.51
     Pembangunan
    0.50
    ượt
    0.49
    ONSO
    0.48
    ICION
    0.48
    }{*}{
    0.48
    mentioned
    0.47
    lato
    0.46
    robe
    0.46
     af
    0.46
    Activations Density 0.163%

    No Known Activations