© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4025
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health assessment and statistical evaluation methods

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

    "individual" or "parts"

    np_acts-logits-general · gemini-2.0-flash

    individual and parts

    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
     surla
    -0.51
    𝟸
    -0.42
    ьаж
    -0.41
     gynnwys
    -0.41
     BitmapFactory
    -0.40
    principalColumn
    -0.40
     transférez
    -0.40
    colorPrimary
    -0.40
     pulumi
    -0.38
     disponibilités
    -0.38
    POSITIVE LOGITS
     individual
    2.44
    individual
    2.23
    Individual
    2.09
     Individual
    2.02
     individually
    2.00
     INDIVIDUAL
    1.94
     individuales
    1.89
     individuale
    1.70
    individ
    1.69
    Individ
    1.69
    Activations Density 1.354%

    No Known Activations