© 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. 20-GEMMASCOPE-RES-16K
    11. 226
    Prev
    Next
    INDEX
    Explanations

    terms related to offsets and shifts, particularly in a programming or technical context

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

    Code relating to offsets or shifts

    np_acts-logits-general · gemini-2.0-flash

    offset and shift

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Literatur
    -0.58
    Спољашње
    -0.57
    rxjs
    -0.56
     ordenador
    -0.56
    huri
    -0.55
    lwjgl
    -0.55
    jsii
    -0.54
    componentWill
    -0.54
     onAnimation
    -0.54
    
    -0.53
    POSITIVE LOGITS
    ConstraintMaker
    0.78
    AttributeSet
    0.70
    IndentedString
    0.67
    contentLoaded
    0.67
    SourceChecksum
    0.67
     offsets
    0.65
    AddTagHelper
    0.63
    HtmlAttribute
    0.62
    cknow
    0.61
     Balik
    0.60
    Activations Density 0.182%

    No Known Activations