© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 12027
    Prev
    Next
    INDEX
    Explanations

    expressions of persistence or overcoming challenges despite setbacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.49
     transitioning
    -0.48
    脚注の使い方
    -0.48
    Personendaten
    -0.46
     básicamente
    -0.43
     snippetHide
    -0.42
     חיצוניים
    -0.42
     pimp
    -0.42
     povezave
    -0.41
     prácticamente
    -0.41
    POSITIVE LOGITS
     그녀
    0.58
     (=
    0.55
    (=
    0.49
     mustn
    0.48
    She
    0.46
     Maths
    0.45
    lend
    0.45
    彼女
    0.45
     pupils
    0.44
    彼女は
    0.44
    Activations Density 0.129%

    No Known Activations