© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8971
    Prev
    Next
    INDEX
    Explanations

    factors and considerations relevant to various contexts and decisions

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

    [word] considered/taken/account, followed by "when" or "in"

    np_acts-logits-general · gemini-2.0-flash

    consider when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.52
    OGND
    -0.50
     calendriers
    -0.47
    waiting
    -0.44
     endregion
    -0.43
    UnusedPrivate
    -0.42
     tôt
    -0.41
    מבר
    -0.41
    rylic
    -0.40
     purpoſe
    -0.40
    POSITIVE LOGITS
     when
    1.41
     هنگام
    1.40
     lors
    1.40
     podczas
    1.34
     during
    1.27
     beim
    1.26
     při
    1.13
     while
    1.11
     أثناء
    1.09
     tijdens
    1.04
    Activations Density 1.313%

    No Known Activations