© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8284
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords related to function definitions and options management in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.66
     utafitiHapana
    -0.59
     Pristupljeno
    -0.59
    HasForeignKey
    -0.58
    AddTagHelper
    -0.56
     externi
    -0.56
    ImageContext
    -0.56
    ,’’
    -0.55
     Приступљено
    -0.55
    ChildScrollView
    -0.55
    POSITIVE LOGITS
     *
    2.32
     *
    
    1.10
     *"
    1.06
     *}
    1.02
     *\
    1.00
     $*$
    0.98
     *$
    0.98
     *_
    0.90
     *,
    0.85
     *);
    0.84
    Activations Density 0.773%

    No Known Activations