© 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. 24-GEMMASCOPE-RES-16K
    6. 7813
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpersonal relationships and their dynamics

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

    preceding "the" or "this"

    np_acts-logits-general · gemini-2.0-flash

    list followed by article

    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
    Blockly
    -0.57
     rū
    -0.56
    WindowConstants
    -0.56
     kılıf
    -0.53
     kaplama
    -0.51
    Which
    -0.50
    期刊论文
    -0.49
    Rè
    -0.48
     Which
    -0.48
    __*/
    -0.48
    POSITIVE LOGITS
    adays
    0.85
     Normdatei
    0.75
    WriteTagHelper
    0.72
     there
    0.65
    BibitemShut
    0.64
     they
    0.63
    MessageTagHelper
    0.59
     someone
    0.59
    zitter
    0.58
     another
    0.58
    Activations Density 0.628%

    No Known Activations