© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6203
    Prev
    Next
    INDEX
    Explanations

    details related to scientific measurements and data analysis, particularly in relation to bonding strength and material properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.58
     ujednoznacz
    -0.56
    ".$_
    -0.54
     đương
    -0.53
     invite
    -0.49
    نوش
    -0.47
     незавершена
    -0.47
    ljen
    -0.47
     undangan
    -0.47
     téc
    -0.47
    POSITIVE LOGITS
     values
    1.16
     valores
    0.98
     valori
    0.94
     Values
    0.91
    values
    0.91
     valeurs
    0.90
     decreases
    0.90
     trend
    0.89
     slightly
    0.87
    valores
    0.86
    Activations Density 3.135%

    No Known Activations