© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 729
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure, particularly pertaining to parsing and defining variables

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

    Code, symbols, and uncommon words/tokens

    np_acts-logits-general · gemini-2.0-flash

    fig

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    MessageTagHelper
    -0.67
     nahilalakip
    -0.58
    esModule
    -0.54
    addCriterion
    -0.54
     strerror
    -0.53
    ViewFeatures
    -0.53
    存于互联网档案馆
    -0.51
    NullException
    -0.50
    évaluateur
    -0.50
     PSE
    -0.50
    POSITIVE LOGITS
    GenerationType
    0.36
    RTSN
    0.35
    charCode
    0.35
    Referanser
    0.34
     defStyleAttr
    0.32
     الرياضيه
    0.32
     "..\..\
    0.31
    toCharArray
    0.30
    accompag
    0.30
     doen
    0.28
    Activations Density 0.453%

    No Known Activations