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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1230
    Prev
    Next
    INDEX
    Explanations

    references to movies and their portrayal within a critical or contextual framework

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

    phrases that describe something being made to appear or look different from reality through deception or manipulation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뀜
    -0.48
    TokenNameLPAREN
    -0.36
    EMPLO
    -0.36
    ]")]
    -0.35
    transQ
    -0.34
     trăm
    -0.34
    뀔
    -0.32
    abstractmethod
    -0.32
     chng
    -0.32
    Personendaten
    -0.32
    POSITIVE LOGITS
     sounds
    1.70
     sounding
    1.69
     sounded
    1.65
     looks
    1.59
    看起來
    1.53
    sounds
    1.48
     Looks
    1.46
    看起来
    1.44
    looks
    1.41
     Sounds
    1.41
    Activations Density 0.499%

    No Known Activations