© 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. 14-GEMMASCOPE-RES-16K
    11. 12593
    Prev
    Next
    INDEX
    Explanations

    specific markers or identifiers in scientific contexts, particularly in relation to conditions, treatments, or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -1.34
    ة
    -0.83
    ς
    -0.80
    GLOBALS
    -0.74
    ená
    -0.74
    ING
    -0.72
    Parameteri
    -0.71
    en
    -0.71
    ;}
    -0.69
    DateTimeField
    -0.69
    POSITIVE LOGITS
    <h1>
    1.76
    $",
    0.85
     Ack
    0.84
    {}".
    0.84
    </h1>
    0.76
    🔥🔥
    0.75
    </s>
    0.74
     NAC
    0.74
     Dunk
    0.74
     Momb
    0.74
    Activations Density 0.234%

    No Known Activations