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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 872
    Prev
    Next
    INDEX
    Explanations

    negative phrases and expressions indicating difficulty or challenges

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

    negations or contractions expressing absence, denial, or lack (using "n't", "not", "don't", "hasn't", etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.67
     صوتيه
    -0.57
    verwijspagina
    -0.55
    rungsseite
    -0.52
    发表于
    -0.50
     مشين
    -0.49
     useful
    -0.49
    كويكب
    -0.47
     útil
    -0.45
    Personendaten
    -0.44
    POSITIVE LOGITS
     hesitation
    0.58
    nocache
    0.55
     underestimate
    0.53
     fail
    0.53
     disappointments
    0.52
    contentLoaded
    0.51
     understatement
    0.51
     disappointment
    0.50
     boundaries
    0.50
     boring
    0.50
    Activations Density 0.269%

    No Known Activations