© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4248
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or intentions associated with communication and expression

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

    Followed by infinitive form of a verb

    np_acts-logits-general · gemini-2.0-flash

    actions to do

    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
     znal
    -0.34
     nocturna
    -0.32
     Universitaria
    -0.31
     laikā
    -0.30
     żyw
    -0.30
     znaj
    -0.30
     Absicht
    -0.28
     benutzen
    -0.28
     Staats
    -0.28
     umgekehrt
    -0.28
    POSITIVE LOGITS
    ViewFeatures
    0.79
    AddTagHelper
    0.69
    DockStyle
    0.68
    ########.
    0.68
    hoeddwyd
    0.68
    ChildScrollView
    0.67
    IUrlHelper
    0.65
    GHIJKLM
    0.64
    󠁮
    0.63
    
    0.63
    Activations Density 0.123%

    No Known Activations