© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14318
    Prev
    Next
    INDEX
    Explanations

    the word "that" repeated in sentences

    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
    161
    +0.16
    0.5%
    32
    +0.11
    0.4%
    1350
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.16
    0.08
    1023
    +0.11
    0.07
    32
    +0.10
    0.06
    Negative Logits
     wien
    -1.29
     dises
    -1.28
     franz
    -1.25
     fluo
    -1.25
     dispen
    -1.21
     fischer
    -1.21
     blos
    -1.19
     ardu
    -1.18
     aton
    -1.15
     unan
    -1.14
    POSITIVE LOGITS
     happens
    0.84
     happened
    0.81
     is
    0.80
     might
    0.77
     isn
    0.76
     doesn
    0.75
     shouldn
    0.75
     would
    0.74
     wouldn
    0.74
     hasn
    0.74
    Activations Density 0.155%

    No Known Activations