© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8312
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks

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

    Followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    numbers or code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.49
    <bos>
    -0.47
    AISSEE
    -0.38
    ResumeLayout
    -0.36
    従
    -0.35
     вре
    -0.34
     Site
    -0.34
     The
    -0.34
     Corre
    -0.34
     Your
    -0.34
    POSITIVE LOGITS
     estekak
    0.66
     Normdatei
    0.59
    تقاوى
    0.58
    ValueStyle
    0.54
     MainAxisSize
    0.52
     HasFactory
    0.51
     esboço
    0.51
     للاسماء
    0.49
     TextInputType
    0.49
     typelib
    0.48
    Activations Density 0.367%

    No Known Activations