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. 16-GEMMASCOPE-RES-16K
    6. 9135
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated operations or statuses within a code context

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

    Code snippets related to errors or parsing

    np_acts-logits-general · gemini-2.0-flash

    x509 cryptography and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$​
    -0.65
    ")==
    -0.63
    "]];
    -0.61
    ']==
    -0.61
    acce
    -0.60
    //*/
    -0.60
    ————————————————
    -0.58
     pé
    -0.56
    <<<<<<<<
    -0.56
    "):
    
    -0.56
    POSITIVE LOGITS
    s
    0.89
     المعيارى
    0.87
    ″
    0.84
    +#+#
    0.82
     للمعارف
    0.81
    󠁿
    0.79
     utafitiHapana
    0.77
    ′
    0.74
    
    0.74
    XmlAccessType
    0.73
    Activations Density 0.479%

    No Known Activations