© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39667
    Prev
    Next
    INDEX
    Explanations

    terms related to reliability and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.71
    gonic
    -0.71
     Pad
    -0.67
    lanzen
    -0.66
    дз
    -0.66
    fizz
    -0.65
     pad
    -0.65
    Fizz
    -0.62
    getc
    -0.62
    Autowired
    -0.61
    POSITIVE LOGITS
     reliability
    1.30
     Reliable
    1.24
     reliable
    1.24
    Reliable
    1.23
     Reli
    1.16
     Reliability
    1.13
    */;
    1.10
    verläs
    1.07
    Reliability
    1.07
    reliable
    1.06
    Activations Density 0.011%

    No Known Activations