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. 13095
    Prev
    Next
    INDEX
    Explanations

    XML and HTML structure elements and attributes

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

    XML namespace declarations

    np_acts-logits-general · gemini-2.0-flash

    xmlns attribute in XML

    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
    writerow
    -0.48
    setPower
    -0.48
    DateTimeField
    -0.48
    ReusableCell
    -0.47
    יסטוריה
    -0.47
    htë
    -0.47
     demografica
    -0.46
     bains
    -0.45
    subsection
    -0.45
    aventura
    -0.45
    POSITIVE LOGITS
    http
    1.03
     http
    0.81
    AnchorStyles
    0.76
    +#+
    0.73
    httphttps
    0.72
     xmlns
    0.70
     cherchés
    0.66
    tagHelperRunner
    0.63
     "..\..\
    0.60
    NewUrlParser
    0.60
    Activations Density 0.158%

    No Known Activations