© 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. 24-GEMMASCOPE-RES-16K
    11. 7139
    Prev
    Next
    INDEX
    Explanations

    spoken dialogue or quotes within the text

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

    Follows an opening quotation mark

    np_acts-logits-general · gemini-2.0-flash

    quotation marks followed by words

    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
     office
    -0.44
     funds
    -0.42
     and
    -0.40
     locations
    -0.39
     offices
    -0.38
     parts
    -0.36
    ariConfig
    -0.36
    
    -0.36
     particularly
    -0.35
     initially
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.57
    ########.
    0.52
     indisponible
    0.49
    Kaieteur
    0.49
     <<<<<<<<<<<<<<
    0.49
     Administrativna
    0.47
    +#+#
    0.47
    iſchen
    0.46
    iſche
    0.46
    meow
    0.45
    Activations Density 0.099%

    No Known Activations