© 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. 0-GEMMASCOPE-RES-16K
    11. 8735
    Prev
    Next
    INDEX
    Explanations

    statements about value, particularly the concept of value related to various subjects or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.45
     OnInit
    -0.43
     createState
    -0.42
    AndEndTag
    -0.40
     word
    -0.40
     Audiodateien
    -0.37
    gridx
    -0.36
     препратки
    -0.36
     answers
    -0.36
     explanation
    -0.35
    POSITIVE LOGITS
     value
    1.34
     Value
    1.09
     VALUE
    1.06
    value
    1.05
    价值
    1.05
     waarde
    0.98
     ارزش
    0.95
    價值
    0.93
    価値
    0.91
     valeur
    0.90
    Activations Density 0.180%

    No Known Activations