Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3854
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "trim"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.84
    uxxxx
    -0.76
    >>()
    -0.65
     manqué
    -0.64
    HostException
    -0.61
    findpost
    -0.58
     кислота
    -0.58
    messageInfo
    -0.58
     Hari
    -0.57
    })->
    -0.57
    POSITIVE LOGITS
    trim
    3.49
     trim
    3.28
    Trim
    2.98
     Trim
    2.94
     trims
    2.53
     trimmed
    2.29
     TRIM
    2.26
     trimming
    2.25
    TRIM
    2.15
    trimmed
    1.94
    Activations Density 0.073%

    No Known Activations