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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 484
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of options or the necessity to act despite limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.48
     cependant
    -0.42
     CreateTagHelper
    -0.37
    gunos
    -0.36
     however
    -0.35
     Ferner
    -0.35
    ∛
    -0.35
     لديك
    -0.34
     pourtant
    -0.34
     faudrait
    -0.33
    POSITIVE LOGITS
    WithIdentifier
    0.54
     אלא
    0.54
     Butte
    0.54
    ConstraintMaker
    0.53
     cref
    0.52
     but
    0.51
     onPostExecute
    0.50
     protoimpl
    0.50
     except
    0.49
     παρά
    0.47
    Activations Density 0.142%

    No Known Activations