Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 0
    Prev
    Next
    INDEX
    Explanations

    the auxiliary verb "have", especially when followed by other verbs like "been", "shown", or "reported".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    various forms of the verb "have" and its related uses in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.65
     tartalomajánló
    -0.65
    RegressionTest
    -0.63
    Portail
    -0.60
    PerformLayout
    -0.57
    ⓧ
    -0.57
     ExecuteAsync
    -0.56
    tanleria
    -0.54
    ValueStyle
    -0.53
     nakalista
    -0.53
    POSITIVE LOGITS
     been
    0.89
     have
    0.69
     has
    0.66
     telah
    0.63
    been
    0.60
    HasBeen
    0.57
     Been
    0.54
     stato
    0.52
     never
    0.52
    ve
    0.52
    Activations Density 0.333%

    No Known Activations