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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8372
    Prev
    Next
    INDEX
    Explanations

    specific chemical and physical characteristics related to substances and their interactions

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

    Characters following a hyphen

    np_acts-logits-general · gemini-2.0-flash

    shaped C-shaped D-dimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.60
    arangay
    -0.56
     Anſ
    -0.52
     Houſe
    -0.51
     Griechen
    -0.51
    ſelf
    -0.51
     Chriftian
    -0.51
     Theſe
    -0.49
     increí
    -0.49
     Infór
    -0.48
    POSITIVE LOGITS
     informée
    0.40
    tmpdir
    0.37
     graders
    0.36
    ₿
    0.35
    évaluateur
    0.34
    SBATCH
    0.34
    shaped
    0.33
     thermoc
    0.33
    médiaire
    0.33
    AYSIA
    0.32
    Activations Density 0.678%

    No Known Activations