© 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. 24-GEMMASCOPE-RES-16K
    11. 12452
    Prev
    Next
    INDEX
    Explanations

    the presence of clickable elements and their interactions within a user interface context

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

    Followed by the word "text"

    np_acts-logits-general · gemini-2.0-flash

    to text

    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
    DebuggerNonUser
    -0.81
    matchCondition
    -0.65
     للاسماء
    -0.63
    Personendaten
    -0.62
    ⓧ
    -0.61
    DockStyle
    -0.60
     invokingState
    -0.59
     CreateTagHelper
    -0.58
    Rüyada
    -0.57
    曖昧さ回避
    -0.57
    POSITIVE LOGITS
     text
    3.94
    text
    3.55
     Text
    3.28
    Text
    3.10
     TEXT
    2.91
     texts
    2.89
    TEXT
    2.79
     texto
    2.51
     texte
    2.49
     Texts
    2.40
    Activations Density 0.229%

    No Known Activations