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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1167
    Prev
    Next
    INDEX
    Explanations

    prepositions and possessive pronouns that are part of longer phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.19
    0.6%
    1416
    +0.11
    0.4%
    58
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1416
    +0.19
    0.04
    58
    +0.11
    0.04
    1505
    +0.10
    0.04
    Negative Logits
    Sklici
    -0.56
    InkWell
    -0.53
     iconst
    -0.52
    marginVertical
    -0.51
     gustaba
    -0.50
    Groetjes
    -0.49
    Roasted
    -0.48
    OBJETIVOS
    -0.48
    তথ্যসূত্র
    -0.48
     laikā
    -0.48
    POSITIVE LOGITS
     Traité
    0.81
     Mémoires
    0.76
     Messieurs
    0.76
     Mère
    0.70
     intersper
    0.69
     reconno
    0.68
     Chapitre
    0.67
     Annales
    0.67
     Docteur
    0.67
     overla
    0.63
    Activations Density 0.126%

    No Known Activations